diff --git a/examples/FinRL_PortfolioOptimizationEnv_Demo.ipynb b/examples/FinRL_PortfolioOptimizationEnv_Demo.ipynb
new file mode 100644
index 000000000..23bf077c6
--- /dev/null
+++ b/examples/FinRL_PortfolioOptimizationEnv_Demo.ipynb
@@ -0,0 +1,2465 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "3xt6fIDownZs"
+   },
+   "source": [
+    "# A guide Portfolio Optimization Environment\n",
+    "\n",
+    "This notebook aims to provide an example of using PortfolioOptimizationEnv (or POE) to train a reinforcement learning model that learns to solve the portfolio optimization problem.\n",
+    "\n",
+    "In this document, we will reproduce a famous architecture called EIIE (ensemble of identical independent evaluators), introduced in the following paper:\n",
+    "\n",
+    "- Zhengyao Jiang, Dixing Xu, & Jinjun Liang. (2017). A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem. https://doi.org/10.48550/arXiv.1706.10059.\n",
+    "\n",
+    "It's advisable to read it to understand the algorithm implemented in this notebook.\n",
+    "\n",
+    "### Note\n",
+    "If you're using this environment, consider citing the following paper (in adittion to FinRL references):\n",
+    "\n",
+    "- Caio Costa, & Anna Costa (2023). POE: A General Portfolio Optimization Environment for FinRL. In *Anais do II Brazilian Workshop on Artificial Intelligence in Finance* (pp. 132–143). SBC. https://doi.org/10.5753/bwaif.2023.231144.\n",
+    "\n",
+    "```\n",
+    "@inproceedings{bwaif,\n",
+    " author = {Caio Costa and Anna Costa},\n",
+    " title = {POE: A General Portfolio Optimization Environment for FinRL},\n",
+    " booktitle = {Anais do II Brazilian Workshop on Artificial Intelligence in Finance},\n",
+    " location = {João Pessoa/PB},\n",
+    " year = {2023},\n",
+    " keywords = {},\n",
+    " issn = {0000-0000},\n",
+    " pages = {132--143},\n",
+    " publisher = {SBC},\n",
+    " address = {Porto Alegre, RS, Brasil},\n",
+    " doi = {10.5753/bwaif.2023.231144},\n",
+    " url = {https://sol.sbc.org.br/index.php/bwaif/article/view/24959}\n",
+    "}\n",
+    "\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Q0L7FZeWMUHp"
+   },
+   "source": [
+    "## Installation and imports\n",
+    "\n",
+    "To run this notebook in google colab, uncomment the cells below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 127,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "XGHfTt1HMVQw",
+    "outputId": "e5226807-a740-4f22-a279-f466886518ba"
+   },
+   "outputs": [],
+   "source": [
+    "## install finrl library\n",
+    "# !sudo apt install swig\n",
+    "# !pip install git+https://github.com/AI4Finance-Foundation/FinRL.git"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 128,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "-GLganWiMYZ1",
+    "outputId": "b3a7f99c-55dd-4274-c1ce-ab3a8111929a"
+   },
+   "outputs": [],
+   "source": [
+    "## We also need to install quantstats, because the environment uses it to plot graphs\n",
+    "# !pip install quantstats"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 129,
+   "metadata": {
+    "id": "6RqrzokqoanP"
+   },
+   "outputs": [],
+   "source": [
+    "## Hide matplotlib warnings\n",
+    "# import warnings\n",
+    "# warnings.filterwarnings('ignore')\n",
+    "\n",
+    "import logging\n",
+    "logging.getLogger('matplotlib.font_manager').disabled = True"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Cz8DLleGz_TF"
+   },
+   "source": [
+    "#### Import the necessary code libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 130,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "cP5t6U7-nYoc",
+    "outputId": "fd138d3e-222a-4ec5-e008-03a28b89dae9"
+   },
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "\n",
+    "import numpy as np\n",
+    "\n",
+    "from finrl.meta.preprocessor.yahoodownloader import YahooDownloader\n",
+    "from finrl.meta.env_portfolio_optimization.env_portfolio_optimization import PortfolioOptimizationEnv\n",
+    "from finrl.agents.portfolio_optimization.models import DRLAgent\n",
+    "from finrl.agents.portfolio_optimization.architectures import EIIE\n",
+    "\n",
+    "device = 'cuda:0' if torch.cuda.is_available() else 'cpu'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "TY2yhvpASEyo"
+   },
+   "source": [
+    "## Fetch data\n",
+    "\n",
+    "In his paper, *Jiang et al* creates a portfolio composed by the top-11 cryptocurrencies based on 30-days volume. Since it's not specified when this classification was done, it's difficult to reproduce, so we will use a similar approach in the Brazillian stock market:\n",
+    "\n",
+    "- We select top-10 stocks from Brazillian stock market;\n",
+    "- For simplicity, we disconsider stocks that have missing data for a days in period 2011-01-01 to 2019-12-31 (9 years);"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 131,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "H11UjCstSFwm",
+    "outputId": "3d27b983-d1e0-41af-b20a-421be40e469f"
+   },
+   "outputs": [],
+   "source": [
+    "TOP_BRL = [\n",
+    "    \"VALE3.SA\", \"PETR4.SA\", \"ITUB4.SA\", \"BBDC4.SA\",\n",
+    "    \"BBAS3.SA\", \"RENT3.SA\", \"LREN3.SA\", \"PRIO3.SA\",\n",
+    "    \"WEGE3.SA\", \"ABEV3.SA\"\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 132,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 623
+    },
+    "id": "Bkm96aNsSIji",
+    "outputId": "e3a20095-841e-4c89-c08e-24b9575cfb02"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "10\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "Shape of DataFrame:  (22330, 8)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>date</th>\n",
+       "      <th>open</th>\n",
+       "      <th>high</th>\n",
+       "      <th>low</th>\n",
+       "      <th>close</th>\n",
+       "      <th>volume</th>\n",
+       "      <th>tic</th>\n",
+       "      <th>day</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2011-01-03</td>\n",
+       "      <td>8.632311</td>\n",
+       "      <td>8.728203</td>\n",
+       "      <td>8.630313</td>\n",
+       "      <td>5.265023</td>\n",
+       "      <td>576145</td>\n",
+       "      <td>ABEV3.SA</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2011-01-03</td>\n",
+       "      <td>31.500000</td>\n",
+       "      <td>31.799999</td>\n",
+       "      <td>31.379999</td>\n",
+       "      <td>13.565923</td>\n",
+       "      <td>3313400</td>\n",
+       "      <td>BBAS3.SA</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2011-01-03</td>\n",
+       "      <td>11.809763</td>\n",
+       "      <td>11.927362</td>\n",
+       "      <td>11.724237</td>\n",
+       "      <td>6.708650</td>\n",
+       "      <td>10862336</td>\n",
+       "      <td>BBDC4.SA</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2011-01-03</td>\n",
+       "      <td>18.031555</td>\n",
+       "      <td>18.250118</td>\n",
+       "      <td>17.963253</td>\n",
+       "      <td>10.446303</td>\n",
+       "      <td>10014663</td>\n",
+       "      <td>ITUB4.SA</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2011-01-03</td>\n",
+       "      <td>9.264964</td>\n",
+       "      <td>9.492898</td>\n",
+       "      <td>9.264964</td>\n",
+       "      <td>7.048940</td>\n",
+       "      <td>3320493</td>\n",
+       "      <td>LREN3.SA</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22325</th>\n",
+       "      <td>2019-12-30</td>\n",
+       "      <td>30.549999</td>\n",
+       "      <td>30.709999</td>\n",
+       "      <td>30.150000</td>\n",
+       "      <td>11.107358</td>\n",
+       "      <td>22111600</td>\n",
+       "      <td>PETR4.SA</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22326</th>\n",
+       "      <td>2019-12-30</td>\n",
+       "      <td>6.780000</td>\n",
+       "      <td>6.832000</td>\n",
+       "      <td>6.570000</td>\n",
+       "      <td>6.601397</td>\n",
+       "      <td>8933500</td>\n",
+       "      <td>PRIO3.SA</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22327</th>\n",
+       "      <td>2019-12-30</td>\n",
+       "      <td>47.959999</td>\n",
+       "      <td>48.290001</td>\n",
+       "      <td>47.299999</td>\n",
+       "      <td>44.469746</td>\n",
+       "      <td>2701600</td>\n",
+       "      <td>RENT3.SA</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22328</th>\n",
+       "      <td>2019-12-30</td>\n",
+       "      <td>53.650002</td>\n",
+       "      <td>53.860001</td>\n",
+       "      <td>53.200001</td>\n",
+       "      <td>37.320980</td>\n",
+       "      <td>11928100</td>\n",
+       "      <td>VALE3.SA</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22329</th>\n",
+       "      <td>2019-12-30</td>\n",
+       "      <td>17.700001</td>\n",
+       "      <td>17.740000</td>\n",
+       "      <td>17.330000</td>\n",
+       "      <td>16.431314</td>\n",
+       "      <td>5838200</td>\n",
+       "      <td>WEGE3.SA</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>22330 rows × 8 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             date       open       high  ...    volume       tic  day\n",
+       "0      2011-01-03   8.632311   8.728203  ...    576145  ABEV3.SA    0\n",
+       "1      2011-01-03  31.500000  31.799999  ...   3313400  BBAS3.SA    0\n",
+       "2      2011-01-03  11.809763  11.927362  ...  10862336  BBDC4.SA    0\n",
+       "3      2011-01-03  18.031555  18.250118  ...  10014663  ITUB4.SA    0\n",
+       "4      2011-01-03   9.264964   9.492898  ...   3320493  LREN3.SA    0\n",
+       "...           ...        ...        ...  ...       ...       ...  ...\n",
+       "22325  2019-12-30  30.549999  30.709999  ...  22111600  PETR4.SA    0\n",
+       "22326  2019-12-30   6.780000   6.832000  ...   8933500  PRIO3.SA    0\n",
+       "22327  2019-12-30  47.959999  48.290001  ...   2701600  RENT3.SA    0\n",
+       "22328  2019-12-30  53.650002  53.860001  ...  11928100  VALE3.SA    0\n",
+       "22329  2019-12-30  17.700001  17.740000  ...   5838200  WEGE3.SA    0\n",
+       "\n",
+       "[22330 rows x 8 columns]"
+      ]
+     },
+     "execution_count": 132,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "print(len(TOP_BRL))\n",
+    "\n",
+    "portfolio_raw_df = YahooDownloader(start_date = '2011-01-01',\n",
+    "                                end_date = '2019-12-31',\n",
+    "                                ticker_list = TOP_BRL).fetch_data()\n",
+    "portfolio_raw_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 133,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 444
+    },
+    "id": "2UqpIXsuSKfO",
+    "outputId": "436605d5-bc9e-4038-e3d7-7bdf140033d8"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>date</th>\n",
+       "      <th>open</th>\n",
+       "      <th>high</th>\n",
+       "      <th>low</th>\n",
+       "      <th>close</th>\n",
+       "      <th>volume</th>\n",
+       "      <th>day</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>tic</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ABEV3.SA</th>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>BBAS3.SA</th>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>BBDC4.SA</th>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ITUB4.SA</th>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>LREN3.SA</th>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PETR4.SA</th>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PRIO3.SA</th>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RENT3.SA</th>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>VALE3.SA</th>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>WEGE3.SA</th>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "      <td>2233</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          date  open  high   low  close  volume   day\n",
+       "tic                                                  \n",
+       "ABEV3.SA  2233  2233  2233  2233   2233    2233  2233\n",
+       "BBAS3.SA  2233  2233  2233  2233   2233    2233  2233\n",
+       "BBDC4.SA  2233  2233  2233  2233   2233    2233  2233\n",
+       "ITUB4.SA  2233  2233  2233  2233   2233    2233  2233\n",
+       "LREN3.SA  2233  2233  2233  2233   2233    2233  2233\n",
+       "PETR4.SA  2233  2233  2233  2233   2233    2233  2233\n",
+       "PRIO3.SA  2233  2233  2233  2233   2233    2233  2233\n",
+       "RENT3.SA  2233  2233  2233  2233   2233    2233  2233\n",
+       "VALE3.SA  2233  2233  2233  2233   2233    2233  2233\n",
+       "WEGE3.SA  2233  2233  2233  2233   2233    2233  2233"
+      ]
+     },
+     "execution_count": 133,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "portfolio_raw_df.groupby(\"tic\").count()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "pM829994GWo3"
+   },
+   "source": [
+    "### Instantiate Environment\n",
+    "\n",
+    "Using the `PortfolioOptimizationEnv`, it's easy to instantiate a portfolio optimization environment for reinforcement learning agents. In the example below, we use the dataframe created before to start an environment."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 134,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Normalizing ['close', 'high', 'low'] by previous time...\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_portfolio = portfolio_raw_df[[\"date\", \"tic\", \"close\", \"high\", \"low\"]]\n",
+    "\n",
+    "environment = PortfolioOptimizationEnv(\n",
+    "        df_portfolio,\n",
+    "        initial_amount=100000,\n",
+    "        comission_fee_pct=0.0025,\n",
+    "        time_window=50,\n",
+    "        features=[\"close\", \"high\", \"low\"]\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Instantiate Model\n",
+    "\n",
+    "Now, we can instantiate the model using FinRL API. In this example, we are going to use the EIIE architecture introduced by Jiang et. al.\n",
+    "\n",
+    ":exclamation: **Note:** Remember to set the architecture's `time_window` parameter with the same value of the environment's `time_window`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 135,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 1000,
+     "referenced_widgets": [
+      "750b2ea28d2a439db3fc5034927dbce2",
+      "c172e120fc5e4f9ab13bf8599d868b5f",
+      "4b2aa7128c5d4d15bb794eb76faccd6a",
+      "317393fb13c0449abfff29a4949553a0",
+      "8cb75a82e5374c51b1f47a6e15783177",
+      "9cb3d937be5d4f7cac192b392218ef37",
+      "b27b9cc333ac44a5bb2cec60d02f16c0",
+      "6a1187acb99d44c68e27cd5aad879ff1",
+      "6a5c9dbaddc441d390d4827c170cbe9c",
+      "1f84695a1caf4c80b29eb5eea90bb29a",
+      "a7a6884bfdb642b9b342f7cda49d7d67"
+     ]
+    },
+    "id": "wr82W3E0uQSo",
+    "outputId": "61dcf1f5-7cf0-40b2-85bd-3f7dd943ddc6",
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# set PolicyGradient parameters\n",
+    "model_kwargs = {\n",
+    "    \"lr\": 0.01,\n",
+    "    \"policy\": EIIE,\n",
+    "}\n",
+    "\n",
+    "# here, we can set EIIE's parameters\n",
+    "policy_kwargs = {\n",
+    "    \"k_size\": 4,\n",
+    "    \"time_window\": 50,\n",
+    "    \"device\": device\n",
+    "}\n",
+    "\n",
+    "model = DRLAgent(environment).get_model(\"pg\", model_kwargs, policy_kwargs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Train Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 136,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  0%|          | 0/20 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 361474.125\n",
+      "Final accumulative portfolio value: 3.61474125\n",
+      "Maximum DrawDown: -0.44278663937515705\n",
+      "Sharpe ratio: 0.7851840332671329\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "  5%|▌         | 1/20 [00:10<03:22, 10.65s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 367367.75\n",
+      "Final accumulative portfolio value: 3.6736775\n",
+      "Maximum DrawDown: -0.44544702041693773\n",
+      "Sharpe ratio: 0.7889937808125205\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 10%|█         | 2/20 [00:21<03:11, 10.64s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 341392.1875\n",
+      "Final accumulative portfolio value: 3.413921875\n",
+      "Maximum DrawDown: -0.40833481343659395\n",
+      "Sharpe ratio: 0.7853202449980996\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 15%|█▌        | 3/20 [00:31<03:00, 10.64s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 407335.0\n",
+      "Final accumulative portfolio value: 4.07335\n",
+      "Maximum DrawDown: -0.46804438206034515\n",
+      "Sharpe ratio: 0.8067679859324299\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 20%|██        | 4/20 [00:42<02:50, 10.66s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 420579.9375\n",
+      "Final accumulative portfolio value: 4.205799375\n",
+      "Maximum DrawDown: -0.469598046340988\n",
+      "Sharpe ratio: 0.8051605373339927\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 25%|██▌       | 5/20 [00:53<02:39, 10.61s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 453810.21875\n",
+      "Final accumulative portfolio value: 4.5381021875\n",
+      "Maximum DrawDown: -0.4524471342004611\n",
+      "Sharpe ratio: 0.827235064234536\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 30%|███       | 6/20 [01:03<02:27, 10.53s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 561952.375\n",
+      "Final accumulative portfolio value: 5.61952375\n",
+      "Maximum DrawDown: -0.47880184779386326\n",
+      "Sharpe ratio: 0.8551097402398795\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 35%|███▌      | 7/20 [01:13<02:16, 10.49s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 604649.5\n",
+      "Final accumulative portfolio value: 6.046495\n",
+      "Maximum DrawDown: -0.5322350966854077\n",
+      "Sharpe ratio: 0.7896393741372305\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 40%|████      | 8/20 [01:24<02:05, 10.46s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 577075.4375\n",
+      "Final accumulative portfolio value: 5.770754375\n",
+      "Maximum DrawDown: -0.5981585577705477\n",
+      "Sharpe ratio: 0.6958970690891116\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 45%|████▌     | 9/20 [01:34<01:55, 10.48s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 599269.125\n",
+      "Final accumulative portfolio value: 5.99269125\n",
+      "Maximum DrawDown: -0.6529561182875228\n",
+      "Sharpe ratio: 0.6859310166769742\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 50%|█████     | 10/20 [01:45<01:44, 10.49s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 708887.375\n",
+      "Final accumulative portfolio value: 7.08887375\n",
+      "Maximum DrawDown: -0.6771446995966863\n",
+      "Sharpe ratio: 0.7210440705113376\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 55%|█████▌    | 11/20 [01:55<01:34, 10.48s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 865635.3125\n",
+      "Final accumulative portfolio value: 8.656353125\n",
+      "Maximum DrawDown: -0.681352361247958\n",
+      "Sharpe ratio: 0.7630764231791436\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 60%|██████    | 12/20 [02:06<01:23, 10.47s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 973545.25\n",
+      "Final accumulative portfolio value: 9.7354525\n",
+      "Maximum DrawDown: -0.6725992234520531\n",
+      "Sharpe ratio: 0.7939690978360787\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 65%|██████▌   | 13/20 [02:17<01:13, 10.57s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 1138418.125\n",
+      "Final accumulative portfolio value: 11.38418125\n",
+      "Maximum DrawDown: -0.6711483054281047\n",
+      "Sharpe ratio: 0.8222353508533622\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 70%|███████   | 14/20 [02:27<01:03, 10.60s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 1402175.5\n",
+      "Final accumulative portfolio value: 14.021755\n",
+      "Maximum DrawDown: -0.662336537704288\n",
+      "Sharpe ratio: 0.86537519568219\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 75%|███████▌  | 15/20 [02:38<00:52, 10.55s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 1698154.375\n",
+      "Final accumulative portfolio value: 16.98154375\n",
+      "Maximum DrawDown: -0.6535264151004916\n",
+      "Sharpe ratio: 0.9058785622283346\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 80%|████████  | 16/20 [02:48<00:42, 10.50s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 2016288.25\n",
+      "Final accumulative portfolio value: 20.1628825\n",
+      "Maximum DrawDown: -0.6440322262060848\n",
+      "Sharpe ratio: 0.9428484491387145\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 85%|████████▌ | 17/20 [02:58<00:31, 10.48s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 2346726.5\n",
+      "Final accumulative portfolio value: 23.467265\n",
+      "Maximum DrawDown: -0.634284880387107\n",
+      "Sharpe ratio: 0.9759229657591402\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 90%|█████████ | 18/20 [03:09<00:20, 10.43s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 2695615.75\n",
+      "Final accumulative portfolio value: 26.9561575\n",
+      "Maximum DrawDown: -0.6263110274122448\n",
+      "Sharpe ratio: 1.0062827959000722\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " 95%|█████████▌| 19/20 [03:19<00:10, 10.43s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 3077908.25\n",
+      "Final accumulative portfolio value: 30.7790825\n",
+      "Maximum DrawDown: -0.620180266358566\n",
+      "Sharpe ratio: 1.0358328134696104\n",
+      "=================================\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 20/20 [03:30<00:00, 10.50s/it]\n"
+     ]
+    }
+   ],
+   "source": [
+    "DRLAgent.train_model(model, episodes=20)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "JE7X3qEeXOr4"
+   },
+   "source": [
+    "### Save Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 137,
+   "metadata": {
+    "id": "YcWuPgPvXNpP"
+   },
+   "outputs": [],
+   "source": [
+    "torch.save(model.train_policy.state_dict(), \"policy_EIIE.pt\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "7FRK9A98XVck"
+   },
+   "source": [
+    "## Test Model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "pstJ-uY1_7VY"
+   },
+   "source": [
+    "### Define test period\n",
+    "In this work, we are going to use three annual test periods: the year of 2020, 2021 and 2022. To get data from Yahoo Finance, we do just like in the training data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 138,
+   "metadata": {
+    "id": "yf7yyFWLfEgh"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "Shape of DataFrame:  (2480, 8)\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "Shape of DataFrame:  (2470, 8)\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "[*********************100%%**********************]  1 of 1 completed\n",
+      "Shape of DataFrame:  (2500, 8)\n"
+     ]
+    }
+   ],
+   "source": [
+    "portfolio_2020_raw_df = YahooDownloader(start_date = '2020-01-01',\n",
+    "                                end_date = '2020-12-31',\n",
+    "                                ticker_list = TOP_BRL).fetch_data()\n",
+    "portfolio_2021_raw_df = YahooDownloader(start_date = '2021-01-01',\n",
+    "                                end_date = '2021-12-31',\n",
+    "                                ticker_list = TOP_BRL).fetch_data()\n",
+    "portfolio_2022_raw_df = YahooDownloader(start_date = '2022-01-01',\n",
+    "                                end_date = '2022-12-31',\n",
+    "                                ticker_list = TOP_BRL).fetch_data()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 139,
+   "metadata": {
+    "id": "WkbmU7ug87qe"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>date</th>\n",
+       "      <th>open</th>\n",
+       "      <th>high</th>\n",
+       "      <th>low</th>\n",
+       "      <th>close</th>\n",
+       "      <th>volume</th>\n",
+       "      <th>day</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>tic</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ABEV3.SA</th>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>BBAS3.SA</th>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>BBDC4.SA</th>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ITUB4.SA</th>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>LREN3.SA</th>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PETR4.SA</th>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PRIO3.SA</th>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RENT3.SA</th>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>VALE3.SA</th>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>WEGE3.SA</th>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "      <td>248</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          date  open  high  low  close  volume  day\n",
+       "tic                                                \n",
+       "ABEV3.SA   248   248   248  248    248     248  248\n",
+       "BBAS3.SA   248   248   248  248    248     248  248\n",
+       "BBDC4.SA   248   248   248  248    248     248  248\n",
+       "ITUB4.SA   248   248   248  248    248     248  248\n",
+       "LREN3.SA   248   248   248  248    248     248  248\n",
+       "PETR4.SA   248   248   248  248    248     248  248\n",
+       "PRIO3.SA   248   248   248  248    248     248  248\n",
+       "RENT3.SA   248   248   248  248    248     248  248\n",
+       "VALE3.SA   248   248   248  248    248     248  248\n",
+       "WEGE3.SA   248   248   248  248    248     248  248"
+      ]
+     },
+     "execution_count": 139,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "portfolio_2020_raw_df.groupby(\"tic\").count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 140,
+   "metadata": {
+    "id": "xclUdAcr8-Nv"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>date</th>\n",
+       "      <th>open</th>\n",
+       "      <th>high</th>\n",
+       "      <th>low</th>\n",
+       "      <th>close</th>\n",
+       "      <th>volume</th>\n",
+       "      <th>day</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>tic</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ABEV3.SA</th>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>BBAS3.SA</th>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>BBDC4.SA</th>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ITUB4.SA</th>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>LREN3.SA</th>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PETR4.SA</th>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PRIO3.SA</th>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RENT3.SA</th>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>VALE3.SA</th>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>WEGE3.SA</th>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "      <td>247</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          date  open  high  low  close  volume  day\n",
+       "tic                                                \n",
+       "ABEV3.SA   247   247   247  247    247     247  247\n",
+       "BBAS3.SA   247   247   247  247    247     247  247\n",
+       "BBDC4.SA   247   247   247  247    247     247  247\n",
+       "ITUB4.SA   247   247   247  247    247     247  247\n",
+       "LREN3.SA   247   247   247  247    247     247  247\n",
+       "PETR4.SA   247   247   247  247    247     247  247\n",
+       "PRIO3.SA   247   247   247  247    247     247  247\n",
+       "RENT3.SA   247   247   247  247    247     247  247\n",
+       "VALE3.SA   247   247   247  247    247     247  247\n",
+       "WEGE3.SA   247   247   247  247    247     247  247"
+      ]
+     },
+     "execution_count": 140,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "portfolio_2021_raw_df.groupby(\"tic\").count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 141,
+   "metadata": {
+    "id": "Lkl9XcGU8_5i"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>date</th>\n",
+       "      <th>open</th>\n",
+       "      <th>high</th>\n",
+       "      <th>low</th>\n",
+       "      <th>close</th>\n",
+       "      <th>volume</th>\n",
+       "      <th>day</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>tic</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ABEV3.SA</th>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>BBAS3.SA</th>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>BBDC4.SA</th>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ITUB4.SA</th>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>LREN3.SA</th>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PETR4.SA</th>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PRIO3.SA</th>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RENT3.SA</th>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>VALE3.SA</th>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>WEGE3.SA</th>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "      <td>250</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          date  open  high  low  close  volume  day\n",
+       "tic                                                \n",
+       "ABEV3.SA   250   250   250  250    250     250  250\n",
+       "BBAS3.SA   250   250   250  250    250     250  250\n",
+       "BBDC4.SA   250   250   250  250    250     250  250\n",
+       "ITUB4.SA   250   250   250  250    250     250  250\n",
+       "LREN3.SA   250   250   250  250    250     250  250\n",
+       "PETR4.SA   250   250   250  250    250     250  250\n",
+       "PRIO3.SA   250   250   250  250    250     250  250\n",
+       "RENT3.SA   250   250   250  250    250     250  250\n",
+       "VALE3.SA   250   250   250  250    250     250  250\n",
+       "WEGE3.SA   250   250   250  250    250     250  250"
+      ]
+     },
+     "execution_count": 141,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "portfolio_2022_raw_df.groupby(\"tic\").count()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "IFYB9iGwAPSh"
+   },
+   "source": [
+    "### Instantiate different environments\n",
+    "\n",
+    "Since we have three different periods of time, we need three different environments instantiated to simulate them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 142,
+   "metadata": {
+    "id": "HhsL5Cxx9d5s"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Normalizing ['close', 'high', 'low'] by previous time...\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Normalizing ['close', 'high', 'low'] by previous time...\n",
+      "Normalizing ['close', 'high', 'low'] by previous time...\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_portfolio_2020 = portfolio_2020_raw_df[[\"date\", \"tic\", \"close\", \"high\", \"low\"]]\n",
+    "df_portfolio_2021 = portfolio_2021_raw_df[[\"date\", \"tic\", \"close\", \"high\", \"low\"]]\n",
+    "df_portfolio_2022 = portfolio_2022_raw_df[[\"date\", \"tic\", \"close\", \"high\", \"low\"]]\n",
+    "\n",
+    "environment_2020 = PortfolioOptimizationEnv(\n",
+    "    df_portfolio_2020,\n",
+    "    initial_amount=100000,\n",
+    "    comission_fee_pct=0.0025,\n",
+    "    time_window=50,\n",
+    "    features=[\"close\", \"high\", \"low\"]\n",
+    ")\n",
+    "\n",
+    "environment_2021 = PortfolioOptimizationEnv(\n",
+    "    df_portfolio_2021,\n",
+    "    initial_amount=100000,\n",
+    "    comission_fee_pct=0.0025,\n",
+    "    time_window=50,\n",
+    "    features=[\"close\", \"high\", \"low\"]\n",
+    ")\n",
+    "\n",
+    "environment_2022 = PortfolioOptimizationEnv(\n",
+    "    df_portfolio_2022,\n",
+    "    initial_amount=100000,\n",
+    "    comission_fee_pct=0.0025,\n",
+    "    time_window=50,\n",
+    "    features=[\"close\", \"high\", \"low\"]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Y4RuS2pRAa4H"
+   },
+   "source": [
+    "### Test EIIE architecture\n",
+    "Now, we can test the EIIE architecture in the three different test periods. It's important no note that, in this code, we load the saved policy even though it's not necessary just to show how to save and load your model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 143,
+   "metadata": {
+    "id": "JeRy__TI9CAs"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 104272.4921875\n",
+      "Final accumulative portfolio value: 1.042724921875\n",
+      "Maximum DrawDown: -0.3134186860319077\n",
+      "Sharpe ratio: 0.36180776300706646\n",
+      "=================================\n",
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 42020.9765625\n",
+      "Final accumulative portfolio value: 0.420209765625\n",
+      "Maximum DrawDown: -0.5931160156249999\n",
+      "Sharpe ratio: -3.141339365788307\n",
+      "=================================\n",
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 52142.08203125\n",
+      "Final accumulative portfolio value: 0.5214208203125\n",
+      "Maximum DrawDown: -0.5175579482110072\n",
+      "Sharpe ratio: -2.195587992293611\n",
+      "=================================\n"
+     ]
+    }
+   ],
+   "source": [
+    "EIIE_results = {\n",
+    "    \"training\": environment._asset_memory[\"final\"],\n",
+    "    \"2020\": {},\n",
+    "    \"2021\": {},\n",
+    "    \"2022\": {}\n",
+    "}\n",
+    "\n",
+    "# instantiate an architecture with the same arguments used in training\n",
+    "# and load with load_state_dict.\n",
+    "policy = EIIE(k_size= 4, time_window= 50, device=device)\n",
+    "policy.load_state_dict(torch.load(\"policy_EIIE.pt\"))\n",
+    "\n",
+    "# 2020\n",
+    "DRLAgent.DRL_validation(model, environment_2020, policy=policy)\n",
+    "EIIE_results[\"2020\"][\"value\"] = environment_2020._asset_memory[\"final\"]\n",
+    "\n",
+    "# 2021\n",
+    "DRLAgent.DRL_validation(model, environment_2021, policy=policy)\n",
+    "EIIE_results[\"2021\"][\"value\"] = environment_2021._asset_memory[\"final\"]\n",
+    "\n",
+    "# 2022\n",
+    "DRLAgent.DRL_validation(model, environment_2022, policy=policy)\n",
+    "EIIE_results[\"2022\"][\"value\"] = environment_2022._asset_memory[\"final\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "LZc5PpbaBU-J"
+   },
+   "source": [
+    "### Test Uniform Buy and Hold\n",
+    "For comparison, we will also test the performance of a uniform buy and hold strategy. In this strategy, the portfolio has no remaining cash and the same percentage of money is allocated in each asset."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 144,
+   "metadata": {
+    "id": "ntHO_UIs-83T"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 403056.28125\n",
+      "Final accumulative portfolio value: 4.0305628125\n",
+      "Maximum DrawDown: -0.47875244091762803\n",
+      "Sharpe ratio: 0.7853090877067095\n",
+      "=================================\n",
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 171126.8125\n",
+      "Final accumulative portfolio value: 1.711268125\n",
+      "Maximum DrawDown: -0.250801953125\n",
+      "Sharpe ratio: 1.712443490118881\n",
+      "=================================\n",
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 95723.921875\n",
+      "Final accumulative portfolio value: 0.95723921875\n",
+      "Maximum DrawDown: -0.17293185561981794\n",
+      "Sharpe ratio: -0.1558444284474649\n",
+      "=================================\n",
+      "=================================\n",
+      "Initial portfolio value:100000\n",
+      "Final portfolio value: 114157.5\n",
+      "Final accumulative portfolio value: 1.141575\n",
+      "Maximum DrawDown: -0.16239865532322129\n",
+      "Sharpe ratio: 0.8449068899613046\n",
+      "=================================\n"
+     ]
+    }
+   ],
+   "source": [
+    "UBAH_results = {\n",
+    "    \"train\": {},\n",
+    "    \"2020\": {},\n",
+    "    \"2021\": {},\n",
+    "    \"2022\": {}\n",
+    "}\n",
+    "\n",
+    "PORTFOLIO_SIZE = len(TOP_BRL)\n",
+    "\n",
+    "# train period\n",
+    "terminated = False\n",
+    "environment.reset()\n",
+    "while not terminated:\n",
+    "    action = [0] + [1/PORTFOLIO_SIZE] * PORTFOLIO_SIZE\n",
+    "    _, _, terminated, _ = environment.step(action)\n",
+    "UBAH_results[\"train\"][\"value\"] = environment._asset_memory[\"final\"]\n",
+    "\n",
+    "# 2020\n",
+    "terminated = False\n",
+    "environment_2020.reset()\n",
+    "while not terminated:\n",
+    "    action = [0] + [1/PORTFOLIO_SIZE] * PORTFOLIO_SIZE\n",
+    "    _, _, terminated, _ = environment_2020.step(action)\n",
+    "UBAH_results[\"2020\"][\"value\"] = environment_2020._asset_memory[\"final\"]\n",
+    "\n",
+    "# 2021\n",
+    "terminated = False\n",
+    "environment_2021.reset()\n",
+    "while not terminated:\n",
+    "    action = [0] + [1/PORTFOLIO_SIZE] * PORTFOLIO_SIZE\n",
+    "    _, _, terminated, _ = environment_2021.step(action)\n",
+    "UBAH_results[\"2021\"][\"value\"] = environment_2021._asset_memory[\"final\"]\n",
+    "\n",
+    "# 2022\n",
+    "terminated = False\n",
+    "environment_2022.reset()\n",
+    "while not terminated:\n",
+    "    action = [0] + [1/PORTFOLIO_SIZE] * PORTFOLIO_SIZE\n",
+    "    _, _, terminated, _ = environment_2022.step(action)\n",
+    "UBAH_results[\"2022\"][\"value\"] = environment_2022._asset_memory[\"final\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "kBMM7hAHC6rq"
+   },
+   "source": [
+    "### Plot graphics"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 145,
+   "metadata": {
+    "id": "n8YrDNpeC71w"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA1cAAAIsCAYAAAAeUFNGAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAADMKklEQVR4nOzdd3gU1foH8O9sy6b3kEBoV0poIhKVjpQI0lUEu6KCFy/ixd7F8tOLiteuXLuCFQFpUsWCFBXEAtJrQkJIr1tnfn9sdrKzJdlsdrOb5Pt5Hh93zsycOQlL2DfvOe8RJEmSQERERERERI2iCvYAiIiIiIiIWgIGV0RERERERH7A4IqIiIiIiMgPGFwRERERERH5AYMrIiIiIiIiP2BwRURERERE5AcMroiIiIiIiPyAwRUREREREZEfMLgiIiIiIiLyAwZXREQ+mD9/PjIzMxX/XXDBBRg6dCiuueYafPrppxBF0a/PPHz4MG688UYMGjQIo0ePRmFhoV/7bw1+/fVXZGZmYunSpX7rs7i4GBUVFX7r7/Tp08jMzMSrr77a4HtnzZqFMWPG+G0soWbVqlXIzMzEtm3b/NZnZmYmHnzwQb/1R0StmybYAyAias7uuusuxMXFAQAkSUJ1dTW2bNmChQsX4vTp07j77rv99qwnnngCR48exaxZsxATE4PExES/9d1adO7cGU8++SR69+7tl/5++uknPProo3jvvfcQFRXllz7j4+Px5JNP4pxzzmnwvTfffDMqKyv9Mo5Q1K9fPzz55JPo1q1bsIdCROQWgysioka4+OKL0bZtW0XbZZddhptvvhlffPEFbrzxRiQlJfnlWYcOHcKFF16Im266yS/9tUaJiYkYN26c3/r766+/UFZW5rf+ACA8PNznMQ4YMMCvYwk16enpSE9PD/YwiIg84rRAIiI/U6vVyMrKgtVqxZ9//um3fi0WCyIjI/3WHxEREfkXgysiogBQqWw/Xi0Wi9x2/Phx3H///Rg5ciQGDx6M66+/Hhs3blTct2jRImRmZmLr1q0YN24chgwZgnfffReZmZkAgI0bNyIzMxOLFi0CAIiiiE8//RTTpk3DwIEDkZWVhUcffRS5ubmKfidOnIjHH38cCxYswODBgzFmzBgcO3YM8+fPx5QpU7B3717MnDkTgwcPxqWXXooPPvgAkiTh888/x+TJkzF06FDcfPPN2L9/v6LfnJwcPPnkkxg/fjwGDBiA4cOH45///Cd2796tuM4+5i+//BKXX345Bg4ciMsvvxxffvmly/du//79uOuuuzBq1ChcfPHFmDVrFnbt2qW45uzZs3jiiSdwySWXYODAgZg2bRq++OKLev9cnNdc2dc3rVixAu+88w4mTJiAQYMG4eqrr8amTZvq7Gv+/Pl4++23AQBTp07FrFmz5PaJEyfi66+/xqhRozB8+HCsXr0aAHDw4EE8+OCDGDNmDC666CKMGjUK8+bNw+HDh+V+3a258vb757zmyj6WgwcP4vbbb8eQIUMwcuRIPPHEEygpKVHcW1hYKH9Phw4dinvuuQe///47MjMzsWrVqjq/F5mZmXjjjTewePFijB8/HkOGDMEtt9yCX3/91eXav/76C3PnzsXw4cMxZMgQzJo1Cz///LPL99bd99Ddmiuj0YhFixZhypQpGDBgAC699FIsWLDA5esTRREffPABpkyZgsGDB2PGjBn466+/6vy6iIgaitMCiYgCYOfOnQCAjIwMAMCRI0dwyy23ICYmBtdffz3Cw8OxZcsWPPjgg8jPz8e1116ruP/xxx/H1VdfDY1GI68zeeyxx9CnTx9ceeWV6Nq1KwDgsccew7p16zB48GBMnToVeXl5+PLLL7Fjxw588MEHaNeundznt99+i7Zt2+Kuu+5CTk4OOnXqBAAoKSnBnDlzMH78eIwZMwZff/01XnvtNezevRvHjx/HtGnTYDKZ8P777+O+++7DV199Ba1Wi+LiYtx0003QarW44oorkJiYiBMnTmDZsmW44447sHz5cqSkpMjPX716NUwmE6688krExMRg6dKlWLBgAdLS0jBkyBAAwO+//47bb78d0dHRuPrqqxETE4OvvvoKc+bMwZtvvonzzjsPBQUFuOmmm2AymTB16lQkJCRgx44deO6553Dy5Encc889Df7zevfdd6FWqzF9+nSoVCp88sknePDBB9GpUyd06dLF7T2XX345KisrsWXLFsydO1exDqioqAivvfYaZsyYgYqKCpx33nk4evQobr75ZqSmpuK6665DVFQUDh48iBUrVmDv3r1YuXIl9Hq9xzF68/1zp6ysDLNnz8awYcNw1113Yc+ePVi1ahWqq6vxn//8BwBQVVWFmTNnIi8vD9OnT0ebNm2wdu1a3HXXXV5/D9euXYuysjJcffXViIqKwtKlSzFnzhy88soruPDCCwEAv/zyC+bOnYtOnTph5syZAIBvvvkGc+bMwTPPPIPRo0fX+T387bffFM+0WCy44447sHv3bowdOxbXXXcdjhw5gmXLlmHnzp344IMPEBMTAwD4z3/+g2XLlmHEiBG49tpr8ccff+D222/3+usjIvIGg6sGKC4uxpNPPolZs2ahR48eDb5/27Zt2LhxI/Lz8xEbG4uBAwdi/Pjx8m+4iaj5KSsrQ0REBADAarXizJkzWLlyJX766SeMHDkS7du3BwA8//zziIyMxJIlSxAdHQ0AmD59Ou677z688cYbGDduHOLj4+V+r7jiCtx6663ycd++ffHYY48hNTVVXo+zY8cOrFu3DlOmTMEjjzwiXzty5EjMmDED//3vf/HCCy/I7dXV1XjhhRfkMdlVVFTgjjvuwI033gjAVjRg+vTp2LVrF5YtW4Y2bdrI97///vs4ceIEunTpglWrVqG4uBgff/yx4mdieno6nn32WfkDr11hYSGWLVuG1NRUAMCQIUMwadIkrFu3Tg4O/vvf/0Kv12Px4sXyWrUxY8bgsssuw/vvv4+XX34Zr7/+OioqKvDpp5/K692uvPJKLFy4EJ9++ikmT54sB5/eMplM+Oqrr+SiFN27d8c///lPrF+/3mNwde6556JLly7YsmULhg0bJgergC2bcu+992LKlCly24IFC2C1WvHWW28p1uFFRkbigw8+wIEDB9C3b1+PY/Tm++dOZWUl5syZI6/Vu/zyy5GXl4ctW7bAYDBAr9fjk08+wcmTJ/HCCy/g4osvBmB7D958880oLS2t61sny8vLw9tvv41+/foBAMaNG4crrrgCL730Ej755BOIooj/+7//Q5cuXfD+++9Do7F9BJk+fTpmzpyJ559/HsOHD4dWq/X4PXQOrlauXIndu3dj9uzZuOWWW+T2888/Hw8++CDefvtt3H333Th69CiWL1+u+Lty5ZVXYtGiRXL2kYjIH/ip3ktFRUV4+eWXUVVV5dP9W7ZswYcffohevXrhjjvuwJAhQ/DNN9/g66+/9vNIiagpXXfddRg9ejRGjx6NMWPG4IYbbsDy5csxfvx4PP744wBsmaFdu3Zh0KBBsFqtKCkpQUlJCUpLSzFq1CgYjUY502V3wQUX1Pvs7777DgAUHyoBoHfv3hgwYAC2bdsGk8kkt7dp08YlsLIbNWqU/Lpjx44AgF69esmBFQA5C1ZQUAAAuOGGG7BhwwZFYGU2m+XXzj8ve/fuLQcGANC2bVtER0fLJeWLiorw119/4ZJLLlEEH7GxsXj77bfxyCOPQBRFbNmyBX379kVERIT8vSwpKcHIkSMBAD/++KPbr7EuAwcOVFT7s2ccG1Pu3j6V0+6+++7D2rVrFV+bwWCQf8FWXV1dZ3/1ff/qcskllyiOu3fvLr8XAdu/UR06dJADKwDQarW47rrr6u3b7vzzz5cDK8BWPOTSSy/FwYMHkZeXh4MHDyI7OxvDhw9HRUWF/OdWWVmJiy++GIWFhdi3b5+iT+fvobPvvvsOYWFhLuPMyspCx44d5b8jP/30EyRJwtSpUxXXXXPNNRAEweuvkYioPsxc1UMURezYsaNRe6IYjUasWLECWVlZ8g/2jIwMVFVVYd++fbjsssv8NVwiamJPPfUUEhISANjWWUVFRaFTp04IDw+Xr8nOzoYkSVi+fDmWL1/uth/nNVL2Puty+vRphIWFIS0tzeVcp06dsH37dhQUFMjZnbpKtzs+z55RcL5erVYDgGL/LlEUsWjRIuzbtw85OTnIzs6W15k57/Pl7mvS6XSwWq0Aar8HHTp0cLnOXpa8qKgIFRUV2LZtm2IKmSPn76U3HLOGAOTsSWP2KnP+/gmCgIqKCnz00Uc4ePAgcnJykJubK3/99T2rvu9fQ+7V6XSKZ546dUoRGNl17ty53r7t3JWOtwfqubm5clD+1ltv4a233nLbR25uriJ7V992A6dPn0ZaWhrCwsLcjv3777+HKIo4ffo0ALhUGoyOjvZbNU8iIoDBVb1ycnKwZMkSDB8+HD169MBrr73mcs3p06exbNkyHDp0CJIkoVu3bpg6dar8G8Z9+/bBYDAofiMIwOU3aETU/PTt29elFLsz+wfYyy67zGNA4Lg2CqgNZOoiSZL8f+ffvtvP2YMEAHVOQfbmec727NmDO+64AzqdDhdeeCHGjh2Lbt26QRRFt+ue6ssQ2L9PdV1nv2bYsGGYPn2622uSk5O9/RJkgZie7dznpk2b8PDDDyM+Ph4XXHABLrjgAmRkZODUqVNYsGBBvf01JsNS370Wi0UOuBy5a/PEHpQ7sgd+arVafn3rrbe6DeQA1wCtvj8X+/vcHVEUodFoFH0YjUaX/cj8vdk3EbVuDK7qkZCQgKeffhrx8fE4cOCAy/n8/Hw899xzSEpKwo033ghJkrB+/Xo899xzeOSRR5CQkIBTp04hLCwMVVVVWLhwIY4ePYqIiAgMGzaMa66IWgHH4Ouiiy5SnMvJycGhQ4cUma6G9Lt9+3bk5ua6BHjHjx+HTqdzycj401tvvQWVSoXPP/9c8dv/devW+dSfPQN36tQpl3OLFy/G6dOncdddd0Gv18NkMrl8L4uLi7F79263ma9Q8OqrryI1NRWffPKJoqS+81S4YEhPT8eJEydc2t39WXiSnZ3t9n5BEBQZo7CwMJc/u8OHDyMvL6/Ogh7utGvXDrt27ZLXjjk6fvy4XFDF/suLkydPKrJhVVVVKCoqatAziYjqwk/19YiMjKzzw8mqVaugVqsxb948nH/++ejfvz/uuusuqFQqrF27FoBtsbgkSXj11VfRs2dPzJ07F4MGDcKaNWs8ThEiopYjKSkJPXv2xLp165CTkyO3S5KE5557Dvfcc49L2WhvDB8+HADw3nvvKdr37t2LnTt3YuDAgW6zCf5SWlqK2NhYxYdVk8kklwf3Zrqao6SkJGRkZGDTpk2K70d5eTk+/vhjnDx5EhqNBkOGDMHPP//ssofYokWLcP/99+PIkSO+f1EN5G6qpCclJSVo06aNIrAqLy+Xy5w39PvlT6NGjcLRo0cVJe+tVqvbUvmebNu2DcePH5ePCwoK8M033+D8889HQkICevbsieTkZHzxxReKjZdNJhMee+wx3H///YqtC7wxbNgwGI1GLFmyRNG+adMmnDx5EsOGDQNg2+xbrVbjo48+UmS7vvjiizqzX0REDcXMVSPt378f3bp1g16vl/9h1Gq1yMjIkH8babFYYDKZMHHiRHlRcffu3VFVVYXNmzfj0ksvlauNEVHLdN999+G2227DDTfcgGnTpiExMRHfffcdduzYgalTp7pdr1KfQYMGISsrCytWrEBBQQEGDRqE/Px8fPHFF4iJicG///1v/38hDoYMGYL3338fd999N4YOHYrS0lKsXbtWDiB9KQB0zz334Pbbb8f111+PK664Anq9HsuXL0dFRQXmzJkDAJgzZw5+/fVXzJ49G1deeSXat2+PX375BRs3bsSQIUMwaNAgv36ddYmLiwMALFmyBMOGDZMDXneGDBmC9evX44knnkDfvn1x9uxZfP311yguLgZgq+oXLNdeey3Wrl2LuXPnyqXYN2/ejL179wLwbkqiRqPBrFmzcNVVV0GlUuHLL7+EJElyOXeNRoP77rsPDzzwAK699lpcdtlliIqKwpo1a3Dw4EHccccd8vfTW5MnT8Y333yDN998E8ePH0ffvn1x9OhRLFu2DO3atZMrbqanp+PGG2/Ee++9hzlz5mD48OE4dOgQ1q9f3+BsGRFRXRhcNVJFRQV2797tdq8M+2807T+4e/furTjfq1cv/PDDDzh9+rTHUr9E1DL07t0b77//Pv73v//h888/h9FoRHp6Ou655x5ceeWVPvf79NNPIyMjA6tWrcJ///tfxMTEYNSoUbjtttsUleUCYdasWRBFEevXr8fOnTuRmJiIPn36YOHChbjlllvw888/Y8aMGQ3q87zzzsP//vc/LFq0CO+99x40Gg169eqFJ554Qq7gl56ejg8//BBvvfUW1qxZg4qKCqSmpuK2227D9ddf36RTrceMGYNvv/0W33zzDX7//fc6g6sHHngAERER+PHHH7FhwwYkJydj4MCBuP7663HllVfi559/VpSub0pRUVH43//+h5deegnLli2D1WrFwIEDcf/99+PJJ59UrN3zZNiwYcjIyMAnn3wCg8GA8847D3PmzFGUxR8xYgTeeOMNvPvuu/jwww8hSRI6deqEJ598Ut5ioCG0Wi1ef/11vPvuu9iwYQM2bdqExMRETJ06FTNnzkRsbKx87e23346UlBR89tlneOmll9CpUycsXLhQrupJROQPgsR8uNcOHDiAF198Ef/+97/l0sN33303unfv7lLm1q5Tp0747rvv8Omnn+Lhhx9WrAXYtWsX/ve//7m0ExERNaWSkhJER0e7FDbZsGEDHnroIbz55pt1bg+QmZmJrKwsPPvss4EeKhFRSOOaq0bq1q0bcnNz0b59e3Tq1En+7/vvv8evv/4KwJahEgQBv/zyi+LeP/74AxEREfVWGiMiIgqkV155BSNGjHCZmrhx40ao1Wp07949SCMjImpeOC2wkcaPH48FCxbg1VdfxcUXXwydTodt27bhl19+wU033QTAVhb44osvxsaNG6HRaNCtWzd5wfmVV14Z0AXnRERE9bn00kuxatUqzJo1CxMnToRGo8H27dvx/fffY+bMmYiJiQn2EImImgV+qm+k9PR03Hvvvfj666/x/vvvQ5IkpKWlYdasWejfv7983bRp0xAfH4+tW7diw4YNSExMxLXXXouhQ4cGcfRERETABRdcgFdffRUffPAB3n77bZhMJnTq1AmPPfYYJk2aFOzhERE1G1xzRURERERE5Adcc0VEREREROQHDK6IiIiIiIj8gMEVERERERGRHzC4agasVmuwh0DE9yEFHd+DFGx8D1Io4PswtDG4agbOnj0b7CEQ8X1IQcf3IAUb34MUCvg+DG0MroiIiIiIiPyAwRUREREREZEfMLgiIiIiIiLyAwZXREREREREfsDgioiIiIiIyA8YXBEREREREfmBJtgDaAmsVivMZnPA+jebzTAYDAHrn5ofrVYLtVod7GEQERERkQMGV40gSRLy8vJQUlIS0OdYrVZUVFQE9BnU/MTFxSE1NRWCIAR7KEREREQEBleNYg+sUlJSEBEREbAPuWazGVqtNiB9U/MjSRKqqqqQn58PAEhLSwvyiIiIiIgIYHDlM6vVKgdWiYmJAX2WWq1mcEUK4eHhAID8/HykpKRwiiARERFRCGBBCx/Z11hFREQEeSTUWtnfe4Fc70dERERE3mNw1Uhc70LBwvceERERUWhhcEVEREREROQHDK7IxaxZs5CZman4b/jw4bj55pvx3XffBXt4fnHq1ClkZmZi1apVHq9ZtWoVMjMzcerUKbfn33jjDWRmZjboub/++isyMzOxc+fOOq8bN24c5s+f36C+iYiIiCi4WNCC3OratSseeughALbiHWVlZfjmm29w77334rXXXsNFF10U5BESEREREYUWBlfkVkREBPr06aNoGzJkCP744w8sW7aMwRURERERkRNOCySvqVQqREZGKgopzJo1C7fccoviup07dyIzMxO//vorSktLMWjQILz88suKaywWC7KyslzaHe3evRtz5szBiBEjMGDAAEyaNAmLFi2C1WqVr8nMzMTSpUvx7LPPYtSoURg8eDDmzp2LkydPKvratGkTrrrqKgwePBjXXXcdDh061JhvhUd///035s6di1GjRmH48OH497//jcOHD9d5z4EDB3D77bdj6NChmDhxItavXx+QsRERERFRYDG48jNJkmAwWvz7n8m3+yRJatTXYrFY5P+Ki4uxePFinDhxAlOnTvW6j9jYWFx88cVYt26dIijaunUriouLMWnSJLf3HTx4ELNnz0ZsbCyeffZZ/Pe//8V5552Ht99+2yX4eO2111BZWYmnn34aDz30EPbu3YtHH31UPv/999/jwQcfRJcuXfDCCy9g9OjRePzxx73+GqxWq+J7Yf/P+fv766+/YsaMGbBYLHj00Ufx6KOPIj8/HzfffDOOHj3qtu/8/HzMmjUL5eXleOqpp3Dbbbfh5ZdfRmFhodfjIyIiIqLQwGmBfiRJEu5/bSv+Pl4U7KEAAHp0SsCCOUN8Ktn9+++/Y8CAAS7tV199Nfr379+gviZPnowNGzbg559/xsCBAwEAa9asQZ8+fdC5c2e39xw6dAgXXnghnnrqKahUtt8BXHTRRfjhhx+wa9cujBs3Tr62U6dOePrpp+Xj06dPY9GiRSgsLERiYiLeffddZGRkyNfYx/Daa695NX5vg8lXX30V7dq1w6uvvipv6nvRRRdhypQpePPNN/H888+73PPpp5/CYrHg5ZdfRkJCAgCgY8eOmDFjhlfPJCIiopbJUlaIgm8WIeaCcYj4x3nBHg55KeSCqx9//BGbN29GQUEBEhISMHz4cIwcObLOAGHevHmoqqpyaX/uuecQGxsbyOG2WN26dcMjjzwCwBY0lpeX46effsJnn30GjUaDO++80+u+LrzwQrRt2xZr1qzBwIEDUVJSgq1bt+Lee+/1eM/48eMxfvx4GI1GnDx5EqdOncKBAwdgtVphMpkU15577rmK45SUFABAdXU1DAYD/v77b8ycOVNxzahRo7wOrl544QW5T0dLly7FypUr5Wft27cPN998sxxYAUB0dDSGDh2KH374wW3fv/32G3r37i0HVgDQp08ft88jIiKi1uPM8oUwZh9A1eHd+MfDS4M9HPJSSAVXW7Zsweeff46xY8ciIyMDR48exdKlS2EwGDB+/Hi39xQUFKCqqgrTp09Hp06dFOeioqKaYNS1BEHAgjlDYDRZ67+4AcwWM7QabYPvC9Opfd5oNjw8HD179lS0DRgwANXV1fjkk09w3XXXITEx0au+BEHAxIkT8cEHH6CyshLr1q2DWq3GJZdc4vEeg8GA559/HmvXroXFYkHbtm1x7rnnQqNxfcvq9XrFsT3TZQ8KJUlCXFyc4pqkpCSvxg4A55xzDtq3b+/S7tiH/TnuvieJiYmoqKhw23dZWRm6du1aZ99ERETU+hizD9S8atwyD2paIRNciaKIdevW4cILL8SUKVMAABkZGcjPz8e3337rMbjKzs4GAPTv3z8kslSCIEAf5t9vq1olQasNjT+qHj16YMWKFcjNzUViYiIEQYAoioprqqurXe6bOHEi3n77bfz444/YuHEjRo4cWWfwu3DhQmzatAnPPPMMBgwYgPDwcABAVlZWg8YbExMDlUqFoiLlVM2SkpIG9VOf6OhoCILgdq1UQUGBx/dmXFycy9gCMT4iIiIiCryQKWghCALuvPNOObCyU6vVsFgsHu87deoUoqOjQyKwag327t0LtVqNdu3aAQAiIyORn5+vuOb33393uS81NRUXXXQRvvrqK/z5558eC1nY7dmzB+effz5GjBghB1Z///03iouLXYK5uoSFheHcc8/Ft99+q7jP0zQ9X4WHh6NHjx7YtGmTonBHRUUFtm7divPOO8/tfRdccAH++usv5OXlyW2HDh1Cbm6uX8dHRERERIEXGukQ2IKrtm3bArBN56qqqsJvv/2GHTt2YOTIkR7vO3XqFMLDw/HGG2/gwIEDkCQJffr0wbRp0xhwNUJVVRX+/PNP+dhsNuP777/HypUrcdlllyE+Ph4A5PVECxcuxPDhw7Fnzx588803bvucPHkyHnjgAbRr167eohi9evXCxo0bsXTpUnTu3BmHDh3Cu+++C0EQ3GbG6jJ79mzcfvvtuOeee3DFFVfgxIkTeO+99xrUhzfmzJmDO+64A3fccQemT58Os9mMDz74AAaDAbNmzXJ7z9VXX40VK1Zg7ty5uO2222C1WvH6669Dp9P5fXxEREREFFghE1w5OnToEBYuXAgA6NChQ51TwbKzs1FRUYEhQ4YgKysLubm5WLVqFV544QU8/PDDLutxyDuHDh1SVKwLCwtDu3btcPvtt+OGG26Q2ydNmoTs7GysXr0ay5YtQ2ZmJp599lmXAhIAMHjwYKhUKkycOLHetWDz5s2DxWLBm2++CbPZjLZt2+KWW27BkSNH8P3338Nisbhdf+VO//798fLLL+ONN97Afffdh3bt2uGxxx7DXXfd5eV3wzsXXnghXn/9dfzvf//DQw89BK1Wi379+mH+/Pno0qWL23vi4uLwzjvvYOHChXjiiScQERGBm266CWvWrPHr2IiIiIgo8ASpsZshBUBxcTHOnj2L4uJirF69GmazGQ899BBiYmJcrj18+DD0ej3S09MVbc8//zyuuuoqjBgxwqcxWK1WnD171uN5s9mM0tJSdOzYMeABnCiKcpGG5uy7777DI488gmXLlrEanh8YDAacOHECsbGx0GobXvCkoYxGI8LCwgL+HCJP+B6kYON7kJqKJFpR/f5c+Th8xisQVLZqxHwfNr2kpCSvf6kfkpmr+Ph4edpZ586d8eijj2Lr1q2KvY3s3GUEunTpgvDwcLnYhS/UajVSU1M9njcYDKioqIBWqw34B1uz2dwkH54D5bvvvsO+ffuwbNkyjB07Vl6vRY1jtVqhVquRnJzcJBnavLy8Ov9OEAUa34MUbHwPUlMRjVU47nAcW52PiHP6AeD7MNSFTDqkuroaO3bsQEFBgaI9JSUFer0excXFLvfYiwU4FgMAbJkei8XS5KXYyb28vDwsWbIE3bp18/tUPCIiIqKWRnIq3mWtLAnOQKjBQia4EgQBH330ETZs2KBoP3LkCAwGg2Lan51arcaSJUtc7vnjjz9gNpvRvXv3gI6ZvHPVVVfhp59+whtvvMEiI0RERET1cVq1IxobVsyLgidkpgXq9XpkZWVh/fr1iIiIQEZGBnJzc7FmzRq0b98egwYNgtlsxqlTp+Rpg+Hh4cjKysKGDRsQGRmJnj17IicnB6tWrUKfPn1cNsElIiIiIgp5kjJzJZoMQRoINVTIBFeArVR3XFwcfvjhB2zatAmRkZHIzMzE5MmTodVqUVBQgAULFmDChAmYOHEiAGDKlCnyPVu2bEFUVBSGDx+OCRMmBPmrISIiIiJqOOdpgZKJmavmIqSCK5VKhREjRnis8JeUlIRFixa53DNy5Mg698IiIiIiImo2nDNXxqogDYQaKmTWXBERERERETgtsBljcEVEREREFEIkp+Cq4s/vXNooNDG4IiIiIiIKJaJrIFW596cgDIQaisEVEREREVEIkZxKsQOAIedgEEZCDcXgioiIiIgolLiZAiio1Sj/Ywus+ceCMCDyVkhVC6TQMX/+fKxevdrjeZ1Oh23btmHVqlV44oknsHz5crRv3x4AMHHiRJx33nl46qmnAACLFi3C22+/Xefz1q1bh6SkJP99AURERETNlZtpgaazp1C6cxUAQOr1GQS1tqlHRV5gcEUexcfH48UXX3R7ThCEBvf3zjvvQK1Wuz0XFxfX4P6IiIiIWiJ3xSuqj+6RXxtPH4a+fY8mHBF5i8EVeaTVatGnTx+/9de7d29oNHzLEREREdWpJrgSNDpIFpPLaVNBNoOrEMU1V0REREREoaRmWqAqPBpRfYa7nK4+/mdTj4i8xDSCn0mSBMls9GufotkMUbI2+D5BG+bT9D1HFovFbbtKpYJK1bDYXBRFt/350hcRERFRS2WvFiioVNCldHQ5b8w+0NRDIi8xuPIjSZJw+qOHQ+YNH5aegbY3PO1zgJWfn48BAwa4PXfzzTfj9ttvb1B/gwYNctt+6aWXysUviIiIiFo9+5orQQWVLtzltLWqrIkHRN5icOV3jcsUhZKEhAS89NJLbs8lJyc3uL8PPvjAbYYqNja2wX0RERERtVhycCVA0OldT1tMEE0GqNyco+BicOVHgiCg7Q1P+31aoNlshlbb8HKbjZ0WqNFo0LNnT5/vd5aRkcGCFkRERET1sFcLFFTuM1cAUPrLWsQPvrwph0Ve4CddPxM8/IahMVSCGiofgisiIiIiaoZEx2mB7j9XWssLYTi1H2Hp3SAIXLseKvgnQUREREQUQiSHNVeCc+ZKawu2ynatw+mPHkbZL2ubeHRUF2auyCOz2Yw///Rc6rNz584N6u+vv/7yuIlweno64uPjG9QfERERUYtUk7kS3GSuBH0kJLNBPi7btQ6xF05o0uGRZwyuyKPi4mLMmDHD4/m33nqrQf3deuutHs89/vjjmDhxYoP6IyIiImqRakqxQ6WCJiZRcUrQR0EqLwzCoMgbDK7Irfnz52P+/PleXescFK1atUpxfNttt+G2227z19CIiIiIWjS5oIUgKApaaJM7QD30OhiW/Z/DtVKTj488Y3BFRERERBRKHApaAECbqfej+tjvSMy6CWfOKrNWluI8SKIVgsr90gtqWixoQUREREQUShymBQJAZPcLkTR2JgS1rXq0Nildcbm5+AwkSYJoqm7SYZIrBldERERERCGkdlqg+4/q9iDLzlJyBseemYrjz18HU+HpgI+PPGNwRUREREQUSiTltEBngkYZXOWvfEV+XfbrNwEbFtWPwRURERERUSixB1cq74IrsapMfq0KC3e+nJoQg6tGYoUWCha+94iIiFomSaytFuiOp+mCAKAKiwjImMg7DK58pNHYCi1aLJYgj4RaK/t7z/5eJCIiohainmmB1Sf2erzVedNhaloMrnykVquhVqtRVlZW/8VEAVBWVia/D4mIiKjlkEQrAHgur24PvtxRa+Q+WD2w6fFX3j4SBAEpKSnIzc1FWFgYIiMjPaZuG8tsNsNqtQakb2p+JElCZWUlysrKkJaWFrD3HREREQWJtWZmlNr9R3V9h54wnNzn/t6aKYWnP3wYxtOH0HHeB1BHRAdilOQGg6tGiI2NRXV1NQoKCnD27NmAPcdqtTI7QQqCICAuLg6xsbHBHgoRERH5mZy58hBcpVx2F6oO/gJ1ZCzOLH3O7b3G04cAAFVHdiO6z/AAjpYcMbhqBEEQkJaWhpSUFJjN5oA95+zZs0hOTg5Y/9T8aLVaBtxEREQtlFSTufI0LVATFY+Y8y+B6exJ15Oite5jCigGV34Q6HUvWq0Wej0XJxIRERG1BpK17syVnTo60c29FkVFYXugRk2DBS2IiIiIiEKJPSBS1R1cudvTShJFQKwNqBhcNS0GV0REREREIcJaVY7iHz8HUH/mShBUEJxLr4sWSJba5SqSyOCqKTG4IiIiIiIKEcU/fCa/ri+4AgCVTpm9kkSrIriyFOXh5OuzUbJ9hd/GSJ4xuCIiIiIiChGWimL5teDFmn5BrVU2iFZI1trgqmz3elhK8lH07cewlBeDAovBFRERERFRKKpnzRUAWErzFceS1QrJYnJ7bclPS/0yLPKMwRURERERUQjyZlqgM+dpgY6sVaWNHRLVg8EVEREREVEIMBVkw5h7RD72JrhKvOQWZYNoheghuFLpoxo1PqofgysiIiIioiAzFeYge9GdsJYV1DZ62ETYUewF4xTH5X9+53FaoLWyeWSurJWlOLv2LZjy3WySHOIYXBERERERBZml+IxLm0/TAk0GRUELR81lWuDpxY+h/LeNOLPixWAPpcEYXBERERERBZkkWl3aBC8yVwAQO3CKsi+T0e11zSVzZS7Itv3/7Kkgj6ThGFwREREREQWbKLo0qcLC3VzoKnHk9eh072L52Fpd5vY6a5X7dvIfBldERERERPUQLSYUb12K/BUveazG1xiSaHFpU4VFen2/oNXLa7RED0GUZKyC6GE9FvkHgysiIiIionqc/vBhFH//KSr2/ojyP7/3/wPcZq4ivL5dEAQ502XPUKkjY12uO/XGv1C2ewMAwJC9HznvPwBDzkFfRkxuMLgiIiIiIqqHKe+o/FqyuF/T1Bhu11xpwxrUh0qnDK408aku11jLi1DwzSIAQO6nT8F4+hBOf/RoQ4dLHjC4IiIiIqIWx1JehOrjf/qlL2PeMcWxPYjxJ38EV0LNuCpqMmvqyDjPz7NaIJkMtgM3UxKDSdDoAAAxmZcGeSQNx+CKiIiIiFqc0x8+jNwl81F58JdG92XP9Ng1NOjxipvgShvfpkFdqJzGpa5j02DJbPRqH62mJkkSJKst2IsbdEWQR9NwDK6IiIiIqMWxlOYDAMp2rW90X6KpWnHsLsvUWJLTmqvkSXO9LsVuZ8/4yH1azUieeAcSRl7vcm31ib/cBnRBJ1oByfa9EDTaIA+m4Rq+M1mA/fjjj9i8eTMKCgqQkJCA4cOHY+TIkRAEweM9Bw4cwPLly5GTk4PIyEgMGjQI48ePh1odetE4ERERETUdS9nZRvchqJzyEdYATKOTlIFOQ4pZ2DkHV5UHf0bK5DsBAEXffqw4d2bpcw3uvyk4VmJkcNVIW7Zsweeff46xY8ciIyMDR48exdKlS2EwGDB+/Hi39xw7dgyvvPIK+vbtiwkTJiA7OxsrV65EdXU1pk+f3sRfARERERGFFElqdBfapPYw5Z+Uj6sO74ZoMiAm89I6EwANIVn9EFxplcFV0piZjRpTMEgOpeIZXDWCKIpYt24dLrzwQkyZMgUAkJGRgfz8fHz77bceg6uVK1ciLS0NM2fOhCAI6N27NzQaDb766iuMGTMGcXFxTfdFEBEREVGIaVxwJZqNqNz3k6Ktcv92VO7fDl2bTtC364rSX9ZCE5eCqIyBjXiQU3Dlw7oulVPmKqrPcPl19PmXoLymBHsok4MrlQaC0PxWMIXMiAVBwJ133ikHVnZqtRoWi/vUq9lsxsGDB9GvXz/Fbw369+8PURSxd+/eQA6ZiIiIiEJdIxNX5qJcj+esZYWoOrQbRZs/Qv5XL8BaVe7zc1zWcTlPRfSC87RAx8/HSWNuRcrkf8sVBV2e74cMnz/Yvw9CM13eE1LBVdu2bZGQkABJklBZWYmtW7dix44dGDZsmNt7CgoKYLFY0KaNspJKfHw8tFotcnM9/2UgIiIiotbA96BBkiTFNDUXajUs5YXyoensCZ+f5biJcFjaOdCldGxwF47TAlOvekR5TqVGVO+h0LrZ+wpA3V9nE5ILe4RgJUNvhMy0QEeHDh3CwoULAQAdOnRAVlaW2+uqq22VW/R6vcs5vV4Pg8EQuEESERERUchrTEam4JtFKP9to+e+zUaIhgr52FyUi/COvX16lj1jE5M5DomX3OzTWi7HzJU6IsbtNZqYRJjOHHNpl8wmIBAl5hvKnrnyIXMXCkIyuEpOTsbdd9+N4uJirF69Gs888wweeughxMQo3yT1/WVpzAJDq9WKs2cbX13GH4xGI/Ly8oI9DGrl+D6kYON7kIKN78HmyWox+/znVlVHYAUAJWfzIDlkrkrzc1Hl47Oq/95he2a1AZYzZzxeV9f70GSszT4VFpdCJbheZ47vAOBXl/YzudlQRcY3cNT+JxbZSuiLEELm71tSUhI0Gu/CppAMruLj4xEfb/vD7dy5Mx599FFs3boV48aNU1wXHm6bM2o0Gl36MBgMbjNa3lKr1UhNdZ82bWp5eXkhMxZqvfg+pGDje5CCje/B5uVozf/VKt8/0x2t53yUTg2zSoQ9dxWhFZDow7NM+SeRXZQNAAjXaZBcRx91vQ9L4hJQVPM6OTUV2gTX68rPpMFd+iApLha6xOC/v41SFXIAqDXaZvn3LWTybdXV1dixYwcKCgoU7SkpKdDr9SguLna5Jzk5GSqVCvn5+Yr24uJimM1mpKWlBXTMRERERBTq/FeoQeO0Xkk0VkGsrp0W6Pi6ISwVRfJrc2GOb4ODclqgoHZfxtxTiXdrpetn7WCQC1o00zVXIRNcCYKAjz76CBs2KEtEHjlyBAaDAenp6S73aLVadOvWDb/99htEh0WAu3btgkqlQkZGRsDHTUREREShxXHpiKX0rGslPh+1v+0lxXHpzlUwF52Wj63VvlULlMy10/mslSU+9QE4VQv0EFwJHtZVFW360Ofn+pXUvAtahExwpdfrkZWVhR9++AErVqzA/v37sWXLFrz55pto3749Bg0aBLPZjKNHjyqyWOPHj8fJkyexaNEi/Pnnn1i3bh2WLVuG4cOHIyEhIYhfEREREREFhVMwVfn3tkZ3GdauGwS1FrEXTlC0O5Zql8y+FVOTrOba140JBB0CkoZuwGupKPH9uX4ksaCF/0yePBlxcXH44YcfsGnTJkRGRiIzMxOTJ0+GVqtFQUEBFixYgAkTJmDixIkAgG7dumH27NlYtWoV3nrrLURHR2Ps2LGYMGFCPU8jIiIiopbIOUBpzP5TdvZpdgkjr4dktaBs1zrX53rYm7U+jmXQUybe4dsAoSzmJqjdf8x3zG794+GvYCkrxMlXZ8FaUQxJtAZ/Op79zy7Y4/BRSAVXKpUKI0aMwIgRI9yeT0pKwqJFi1za+/bti759+wZ6eERERETUHDgsFwEAVZj7jXMbQqipFieoNQg/p5/74MohA9UQksV2X0T3i6Bv34hlLY7BlYfMlb59BsI794U2sR0AQB0VBwgqQBJhrSyFJjq4M7/s+1wJQvMMrppnvo2IiIiIyIPin5YqjgWt7xWk5T4c1jCFtens9hp7kFQX0VgNQ85Bxbowe+aqoVP5XAfpEFwJ7j/mCyo10q55DEljbpGPtQm2InDGnEONe74/NPPMFYMrIiIiImoxjHnHULp9hbLR961PZSp9pPxaE5OI2AGTXK7xJnN1+qNHcPqDB1G5b2vtffbgSq3zdJt3PARU9Qlr1x0AYDp7onHP94PmvuaqeY6aiIiIiMgNU76bAMHa+GqB+g69FMfqiFiXayRr/WuuTPnHAQDlv2+R28SajJdK27jgytf1UuqIaNs4jFWNer5fiKwWSEREREQUEtwFV94EPfVRh0crjt0VjLBWlcF45rhX/SkqBPppWmBE10xok9IRda77+gWe2LNyoqGyUc/3B0niPldERERERCHBnhlyJImND66cgyl3AZtkrELOO3fDkHOw3v4c12fZM0aCxv0eVN5SacOQPuslpEyc07D7wiIV4wgqTgskIiIiIgoNbjfh9cO0wLqCq7Y3Pas4V31kDyzlxTDUUSBCslogSRKKvv8M5bs3AAC0Se0aP06h4QvMVPoIAEDl/h0QTb7t1eUvEgtaEBERERGFBmtVBQCg3c3PI7LHIACN3JjXzjm4ctibyrl8uToyFidfmYnTHzwAY+4Rt91JVjMMp/ahZOuXcpsuqX3jx+kDTUyS/LrywI6gjEFmL8XO4IqIiIiIKHgkSYK1ugwAoIqIkrNN/lhz5ZK5cpjW51imHQBEsxGArdR69fE/3Y/VYoZoUE7DU0fENHqcvtC37yFniqzlxUEZg11t5qp5hinNc9RERERERE4sJWeAmkBKHR4NqGoCogCsudKnd68951TlT3KYWucpsJOsFpfsjCo8qrHD9IkgCIg5bzQAe2AYRGLzLmjhWuaEiIiIiKiZkUQrTr3xLwCAJjYZglYPQW37gC4FYM1VRPeLkHL53QhL/YfLJsWiqVoxLrfjtZohmpXrm1TaxhW0aAx7gFiy9UsIKjXih14ZlHFILMVORERERBRcjtmiqN7DIAhCo6YFSpKkbFApgytBEBDVYxC08akuRSQcgyt4eLZYVSYXsggFgqY2+1b8w2dBG4e9RL27UvfNAYMrIiIiImr2HAOouMFXAKidWuZLKfaqQ78qjhvyYd9w4q/acdXxbMf1WG2uuK8Bo/M/wSlrpggQm5Bktu/51bgNlYOFwRURERERNXtycKXS1E6vswdEDawWmLf0OZz58j+KtvqCq7TrnoQQZitpbi7KdRhX/c+O7jsKkRkXNWiM/uYczOR9uQCF337c5OOQLEa342kuGFwRERERUbMnTyfT1AZBgso+LdD74Eo0G1F1YKdLe33BVXjHXuh094eA4PTx2nl6oRuCTl/vNYGmcgpmDMf/ROn2Ff4pY98AYk3mKpjrzxqDwRURERERNXv2zJVjEFRb0ML7aYGW0rNu272ZFigIKkAS3Y6rLqoQCK6cKx7aNfWmwpKZmSsiIiIioqCSgyvHwhM+lGK3lBW4P+Fj9Trn4EodGefadUgEV+4zRaKxsknHYd+c2VOwF+oYXBERERFRs2ff1FfQ1G7oK2euGjC1zXFzYDtNXBuvMykJo29SNliV/UlOmS0AEHThXo8vUHRJ7d22O290HGhycKXhtEAiIiIiouAQ3U0L9KEUu6gMfpIn3YH2s191KbfuSfS5IxTHklNw5TxtEAiNzJU2KR3hnfq4tIvGpg2u7JsYq5i5IiIiIiIKDjnjpHbIXKkavubKObOk0urlfryhDo9CRJf+tf05PVsS3WWugh9cCYKAtGvnQ5vcQdEuGppuWqClrBDVR36zjYdrroiIiIiIGq9y/06UbFsGSRJReWAnLOVF9d7jrqBF7ZqrBlS8c84s+bCZbcrldyMsPaNmXE6ZKzfBlUob/ODKTnCqdmitLGmyZ59d+6b8WhUW/KmSvmieWx8TERERUYt15qvnAABFW5YAAFQRMeg07/0673FfLdD2uvr4n5BEq3cZKKfgpyGbB9uptGGIvWAc8rP3u2bN3K25CqWy407THwvWvoXI7gOgjogO+KPtWSsAUEXEBvx5gcDMFRERERGFNLGqrN5r5H2u1G4KWpiNKP1lrVfPcp4W6Etw5XifZPFiWmCIT4Er/XlVwJ9hX2tlpw6PCvgzA4HBFRERERE1e7XBlZtpgQDKfl7tZUd+Dq68yFypHCocBp3zJshwM7UxAJyrEqojYgL+zEBgcEVEREREzZ5orAagLA7hOA1Qk5DmVT/OmSXFvlkNYM+gOQYmkiS5nxYYQsGV26KIbgIuf5PM1fJrlT4yJMrT+4LBFRERERGFDHf7QHnDXtVOra+dTmafFmh7bQtg8le9hrwvF9gCHbcDaHxBC8V9jpkrD19baE0LdI2unItcBIJoMtiepQ1DhzsWeV36PtSwoAURERERhQ5rAyr7ORANFQAAlcNaHccslKDRQjQZUPHHFgCApeQMtPGpbjry07TAmoDJUnoWotkIlTbMc3ClDp3MldvUVRMEOvbgShOdCFUzzVoBzFwRERERUR1Kf16Nwk0fNtnzJLEBG/46sFbbMlcqh8yVZDHJrwW1BlaHwhjuCksA/itooaqpAChZzchd/HidzwylzJU+vbtrYxMEV5LJdVpnc8TMFRERERF5VLjRVgI9qs9whLXpFPDnSY3MXKn1kbV9OQRXVYd3I7LHwNpzNZkS1wH4KXOlqy2vbjx9CJaKEjngcrk2hNZcxQ+/GqrwaKij4lGw5g1bY0P2CfORPXPVnLNWADNXREREROQFyewhGPE3Dx/kXaruOd9Ws+bKcVqgJja59n5TNfK/eqH2elNtAQU7S0UJSp2rCnqzN5YbzhsDW8sKap8pqBDVe1ijnxEIKp0e8UOmIrrvSLnNuUx6INQGV807c8XgioiIiIjcUhZ9aJoCA56CKGs9e13Ja64cMlf6Dr0Q1s7NNDe4z1yd+fI/sJTkK9ocC2Q0hPP0NquhEmJ1uW2M4VHQxtdWLwzF4g2CICBhxLUAXMukB4I9eG/u0wIZXBERERGRe45T5JooAPC05irn3XvqvM9qcF1zJQgCYi8c7/Z6x8xV1bHfUfzDFzCePuRyna9T9pyLVIiGCjlAVEfEILrvCACALqWjT/03BXV0AgCgYu+PPldx9JacudI27+CKa66IiIiIyD1FAYamyly5nxZorSyF1VCpWFPlyN2aK8DzminRIXOV98mTvgy1Ts7ZKLG6Qg5Q1eHR0MQmo8Pctz2uwwoFmpgk2wvRitKdqxA3YHLAnmXPJDb3zBWDKyIiIiJyS3Jc/9RUU9fqqhboYcqgJFrlD+eqsAjFOc/BleuaK2eJl9xS7zXeKtm2TA4c7GPU1GSGQpUuuTarZsw9AgCQLOaAFODgmisiIiIiatkcpoI11aqguqoFelqPJVnM8mvBORPkIbiyl/72tJlwWHp3xF4wrq6h1itlyjz5taWsAOaC7DrHFGrUEdGIG3Q5AKBy308o+u5THFtwFaqO7vH7s+zBLqsFEhEREVGLFIzMVV1VASWr2X27Y3DllFVxXPskqLVyOXZrTXEJx3LtCh72pGqIqF5DkDr9YZd2X8u7B4PGYaPlkp+WAgCKf/zS789pKdMCGVwRERERkXtBWHNV155KjkGUot0edAkqCE5lzdURMfLrpAm3Q5vQDgBQ9staVJ/ch+y373Lfp5/2dgr/R1+Ed+qjaAulfa3q43aaXgD2vZKrPTpN62xuGFwRERERkVuSQ3DlKWvk/2f6EFzVZJ8Ejc7lnDoyTn6t0oTBWlUqH+d+/CgsxXnycUz/sbU31rX2qwEElRqp1zwOdXSiQ1vzyVw5b6oM1O4p5k/VJ/cBUP55NUcMroiIiIjIPak20Dn94UNNE2DVBFfa5PbQO2V8PE4LrJlKKGhcgxbHfa8k0SJnSNxJGjvT4Vr/lR4XBAHaBId9rZrRtEB3Aa2/3wfVJ/fKf+6aqDi/9t3UGFwRERERkVvOAYapICfwz6zJlAiCCmnXPA59x9615zysj5IzV2rXzJUgCAhL6wKoNAjvdC6ieg3zbiB+nvrmGOQ1p+AqvHNflzZL6Vm/Blhlu9bLr9VR8X7rNxgYXBERERGRe84BRh3FJvz3zJqATlDZ9opyKKTheVqgrd3TWqa2N/4fOs17D+qIaER0u8DtNUnjb1f2WUfVQl+owhz232pGwZUmJhGRGQNc2s+uXeS/h9izlQltFWvkmiMGV0RERETklvP6J8lP65DqfKY9c6Vy/ZjqKVtiLjpdc4H7qXyCWiNnjgRBgMrNB/jwTr0Vx/4qaGGn0tcWamhOmSsAiimNdhV/bPFb//ZANnbAJL/1GSwMroiIiIjIPadgpa4y6c6MZ47j1KI7UbF/e8Oe6ZC5AoCojIG1z/eQuTq76jUAtulq3nAX3Ki0TlXx/BxcqcMcpwU2n2qBACB42HvK0x5hDWUPZJ0rPTZHDK6IiIiIyC3nNVfeBleSJCLnnbthLshG/lcvNPShtv/XZK6i+41u8PPrY60sdWkTtMr1Wsxc1fK0sa9Ys1dYo9m/1wyuiIiIiKjFcllz5V3AUX30d58f6VjQArBlMyK69Led89e0RDeBk72Mu/3/YWn/8M+zajju39TsgqswD8GVscov/TNzRUREREQtnq+ZK3NRru8PFZWZKwC1BSA8BHe6VFsglDzpDp8fa/9g3+6W5xFz4QQkT/S9L3e0Senya39l4JqKSlcbGCaMvF7ei0o0GfzzAGauiIiIiKjFk5wKWnhZfruuDJO55AxKti3zmPVwzlwBtYGPp6l6ktn2IV8Tm+zV+JzFDZ0mv9YlpSMpawY0fi4JHta2i/y6uVXEE8Jq16MJWr2cyZJM1X7pvyVlrppXTpKIiIiImoxLtUAP+0y5sDpXGbTKH5yLNn+Myv3bUbl/J9rdvMD1XjeZq9rgyjVos1aVwVxoqxao0rqfvlaX8M59kTBseoPvayhBUCF91kuo2PcTInsODvjz/Mkxc6XS6iDUFP/wd+aKwZWfWa1WbNmyBVu3bkVhYSFiYmLQt29fTJo0CXq93u09VVVVmDdvnku7RqPB66+/HughExEREbVcTtMCvf0w7TztTayugDoyFgBQWVM90Jh72MPNymqBAAC12u14AODka/+UXws6958X6+Swj1ag6ZLbI2H4VU32PH9xXHMlaLTycf7yF9Hxrg8aHRTJe4qpGVz51YoVK7B582aMHTsWXbt2RV5eHlatWoWjR4/ivvvug8rNfgenTp0CAMyaNQvx8bXpW6EJ/6IQERERtUTOa66sFcVe3qcMrqpP/IWommyNSh8J0VBZ7zOV0wJtH1mdgzZJkiCZjfKxysvgKunS21DwzSJ7517d05o5VgsU1DqgpgS7aKxC5cGfFeXyfSFJzFz5nclkwubNm5GVlYVJk2wbiPXo0QNRUVF45513cPDgQWRkZLjcd+rUKWi1WvTr189t8EVEREREPnLa58pSVuDdbU5BUP7yFwFRRFTvofVXypPqmhZY9zRF+0bB9Yk5/xI5uOIv5OunqBYoKP8crGWFjX9ACypoETLBVWVlJYYMGYL+/fsr2lNTUwEAJSUlbu/Lzs5Gu3btGFgRERER+ZlzkGStLIEkiTDmHoUupQNUGp37G90Unije+iVMhdlu95hSPNOeuXL8oG2fLuY83dApA6bShtXZt1vMXNXLcbqlJFoVAbK1uqLR/dunBTJz5Ufx8fG45pprXNr37NkDAGjXrp3b+06dOgWNRoMXX3wRR48ehVarRf/+/TF16lSP67SIiIiIyAvOmSKrBeW7N6Jg3f8Q0f0ipE69z+1t7kqNmwtzULJ1qfI6SVRM/7M1uq65sk8LLNm2DJq4NjCc3AtLRTEMx/9s6FfkQhXuXbarNVP8GVmt8vo5ABANjQ+umLlqIkeOHMH69evRp08ftG/f3uW8xWJBbm4uIiIiMGnSJEyYMAEnTpzA6tWrcfr0adxzzz3MaBERERH5yGUantWK0l/XAgCqDuz0fJ+Xmw1LJgMEh811ax5q+7/jtECHQgcFa9/0qu/6JI2fjfLdG5Fw8XV+6a+10KV0QFh6N1T+bStMIjYycyVJojzdlJmrADpw4ADeeOMNJCUl4aabbnJ7jSAImDt3LhISEpCSkgIA6NatG2JiYvDee+/hr7/+wrnnnuvT861WK86ePevr8P3KaDQiLy8v2MOgVo7vQwo2vgcp2Frje9BSpFxPYzZWAw7lzk9tXAxtn9GKa8TyQhh+22A70IYBDgUnnOVln4SqZkNa+RmlJQAAg6H2+22qqn8/JXX3wQ3780ntDfW43iioNAKVzefPNVjvQ/3UxyBVFqNIDAMMEnTDrofph49RVVLQqPFYDv8svy4sKoYKDS+nH2hJSUnQaLwLm0IyuNq2bRuWLFmCtLQ0zJ07F1FRUW6vU6vVbotc9OnTB4BtPZavwZVarZbXewVbXl5eyIyFWi++DynY+B6kYGuN78GyvEg4lrDQqFTQxqegMvcQAMD883K0z1Jmfs78tLj2+ohYWErzPfafnBAHbbzye1pyLApFAMIjI5FS8/0ujolFfXUKO1wxr1UUpwja+9DpmZVl7XAGgFY0N2o8BXvOwF6WJKlNG+gSm/ffsZCbM7dy5Up8+OGH6NatG+655x7ExHjewbqoqAg//PADSkuVCyPNZtvu4Z6CMiIiIiLygvO0QNECtb7uz1fmktpgShVe97WSxeza5qYUO1R15wMiMwa0isAqlKjDowEA1kauuVLsodUCpgWGVHC1bt06rFmzBgMHDsScOXPqLUhhNBqxZMkSbN26VdH+yy+/QBAEdO3aNZDDJSIiImrRXPaVslpc12E5lWt3DHI00Ql19+8muHJb0KKezWWTJ/yrzvPkf/bA2VKcB0sjyrELOscy780/QA6ZaYFnzpzB119/jdTUVAwdOhQnTpxQnE9OToZGo0Fubi6Sk5MRHR2NtLQ0ZGZmYu3atVCpVOjUqRMOHz6MdevWYfjw4UhLSwvSV0NERETU/DkHUhCtLntLSWYjBF04JElC9dE9sFbVzijSJrRFzIUToImMQ9GWxXAmWU0ubRA973Plicq5KAYFnMohg1mybRmSxs6s83pJkmDMPgAIgD69dlmPony+mxL+zU3IBFd79uyBKIrIy8vDc88953L++uuvR3JyMl588UXceOONGDRoEADgpptuwrp167Bt2zasXr0a8fHxmDhxIi655JKm/hKIiIiIWhY31QKds02S2QTowlF9eDfyvnhGebuhEskTbgcA98GVu2mBUs2eR9x/KqQ5lmM3F9df0KLq4C84s3QBAKDtTc9C364bAGXmUxPf/BMjIRNcjRkzBmPGjKn3ukWLFimOtVotJk6ciIkTJwZqaEREREStksu0QNHikrkSzUaoAVSfcN1zKnbgFLf9hqWdA2PuEZe+qo//iZJtK2wHDpkrlZ57UYUaQRCQetUjyPvsaVgriuq9vnDje/Jrw4m/5ODKUmormRLdd2SLWDfHXwkQERERkVsu0wKtFlQd3qW8xmwAAKgjlEXI2s95E7rEtvKxbV2UgJTL7oKg0QEARKfgKnfJfEC0BXSOmauonkMQlnaOfKyOikebqff79DWR/2hiEgEApvyTMBXm1H1tbLL8Wl1Tfl+SJJT9sgYAIJoMgRlkE2NwRURERETuOWWuRGOVyyWi2RYgWQ2VinbnqoLRfUei031LENVzMASNFoCHghZ2jmuuNFq0u7l22YhkMSGi2wVInjQX7W5d6N3XQn6ncSijX/HHd3Vea60ul1/bAylreW3Gy1Lue1GMUMLgioiIiIjckkSLx3OamCTbNTWbBItVZYrziipwNezFCwS1PbhyU9BC7sDzx1TJbIIgCIjuMxxhbTp57oMCSqXRIWHUjQAA45ljHq+TJAmW4jPycfXxPwAAhuz9tReJovNtzRKDKyIiIiJyS7K6r94maPVQ1UwDtE8LNJecUV5Tx/oZ+7TAujJXdVUIlKx1ZLyoSdmD2+ojv8Fa7X7PK7GqTBFIVx38BaKxGtVHf6+9piZIb+4YXBERERGRex5KYwtqtZyFEs0mlO3eAMOJvV536zwtULKYIUmS0zO0Lvepo+JtL1rAZrMthTapvfzaXVETQDkl0O74izfBmHtEPpZaSHAVMtUCiYiIiCi0OFcLlKnUEGqCK0vpWRRt/rBB/dZmrkwoWP8uyn5dC3VUgtM1rsFV2tWP4uyaNxE/bHqDnkeBo4mOh6ANg2Q2wlpR6vYax73PZKIFpvzj8mH4P/oGaIRNi8EVEREREbnlafqd4BBcuQusVOFRLm2K+2sCp+LvP5XbnMt5C2rXj6m6lI5oN+M/dQ+amlz0uSNQtmsdrJXFbs+fXf1GnfdHnXsxEkfeEIihNTlOCyQiIiIit+xV3ZLGzkJYenfFOcdKb46SJ81F+i0v1NmvPXNV5zVupgVSaLKXVrdWlLics1aWwuKwyXBYeobLNcnjZkMV5loApTlicEVEREREbkk1wZWg08vVAQHbGhpPpbOj+wxX7Gnkjrspf75cQ6FBHRUHALBWKDNXhpxDOPHSzfJxWHoG2lw2DxHdLlRc5y5L2VwxuCIiIiIit+yZK5VOj7iBU2pPWC0Qnfa1aghvMleO+1xRaLNnrqoO71a0l+5YoThOvfIBaGKSENG1f21jHSX3m6OW9dUQERERNYAkWlH845eorql0J3mojtdaSeZqALbMVVjqPxTn9G6md3nLq6yUVP8lFBrkKo6QYDp7Sm533OtMHRkHdUQ0ACCy+0Vye8qUfzfFEJtMy8nBERERETVQxd6tKP7hMwBA7IUTULZ7A9KuexL6dl2DPLLQUJu5cl0PkzzhXzj56iz5WJfSEdH9srzqV1B7kblidNVs6JJry7GbCk7JxyqdXm53DKjU4dHo/OAXkMymFrPWyo6ZKyIiImq1LA4b35b+vBqSxYSqI7vruKN1kYMrbc2HZFXt7+U1MYmIvWiSfNxuxgLEZl7qVb/eZa4YXDUXKm0YIjMGAKgtdFJ1aBfKdq2XrxFrNpu2E1TqFhdYAcxcERERUSvmriKdZKxSHBvzjkIdEdtUQwoZoqESYlUZgNppX4JaDUms3ftKUDts5tuAogT2DYjr4rypMIU2dbRtnzJLTVGLvC+eUZyPGzClqYcUFMxcERERUavlLoNidSjUYCkrQM679+Lkq7Na3Yd9U4Ft7Yw6OlFeK+NS1U1VG1wJguB13+H/OA/axLYQtGGI7DnYw1Wt6/vd3Kn1tveIaKhC5YGdinPps/4LXUqHYAyryTFzRURERK2Wu8yVtbJUfm122J/HsucbIO1ml+tbKmt1BQBAU1NmG4AimAJsU7t8oQ6PQvptLwOSBEGlxtF9P8nnwtK6wJh7GBFdMn3qm4JD0NrW0UkWE84sfV5xThPXJhhDCgoGV0RERNRquctcSRajwwW1k3zMu9fAeP5IhLXp1AQjCy5JklC6YyUAW6VAO0HlnLny/aOkIKgAN8mutjc9A8lshCoswue+qenZy+vb/v5Ibs+1BpwWSERERK2Xm6lskqV2TZFkNSvOWT1snNvSVB/eDcNJW3l6uZgFXKcFqrT+/9BsK3TAwKq5kYMrs8n1XAOmjDZ3DK6IiIio1ZKsrvtaKQIqq0VxTnBTkrwlMuYdkV8rMldOwVV031HQJrdH7IDJTTY2Ck32aYGi2VjPlS0bgysiIiJqvWoq32ni2iDtmscBKIMrySm4cg62WirJ4hBgOhTySBhxLQAg+vxLAACqsHC0n/USEkfd0KTjo9CjqslciU7VNlubRq25OnjwIL777jvk5OTghhtuQEREBA4dOoRhw4b5a3xEREREASOJIgAgLO2c2nUhVsdpgcpgynmaYEtl398KsJVkt4vMGIAOd74DdWRcEEZFoUxwE1zpUjoipiYQby18Dq6eeeYZfPzxx5AkCYIgYOzYsSgvL8fcuXMxYsQIvPzyy9DpWs/iNSIiIgptlrJCGLL3I7LHQFsxBUDes0lQa+R9mhyzNs7BlON6rJZMNFXLr503etXU7HlF5EieFugQXLW7dWGrWm8F+DgtcMmSJfjoo49www03YPHixfK+D5mZmbjqqquwZcsWvPvuu34dKBEREVFjZL97D/KXv4jy3zbVNtrXXKnU8noiqa7Mldg6givJIXNlnwpIVBc5c1Wz8TRUmlYXWAE+BlefffYZRo8ejQcffBDnnHOO3J6QkID58+fj0ksvxcqVK/02SCIiIqLGsn/oq/h7GwBAkkQYsg8AsFWos5dlV6y5cspUKdYitWD2zFXyxDnQJrQN8mioOVBHxiqOBU3r3PHJp+Dq+PHjGDzY027awMCBA3H69GmfB0VEREQUKPY1RKU/r0bVoV8A1ARXNRsKi4ZKHP2/K1Cx7ye54IVd61lzZQuuVK2kOiI1niY2RXHsboPu1sCn4ComJgaFhZ73eTh+/Diio6N9HhQRERFRoJjyjkGSRFT89WNto1rtUmY8f/mLLpmq1pC5Es1GGO0ZPQZX5CVBEBA3dFrtsZqZK68NGzYMn376KXJzc13O/f777/j000/rzGwRERERBY+Ewg3vATWVAgFl5kpxZStcc2U6c1x+rQ7nL8vJe7qkdPl1a8nyOvMppJw3bx62bduGSZMmoV+/fhAEAYsXL8a7776L7du3IzY2FnPnzvX3WImIiIh8YrUvsq9R9us30Ca3l48lUXS7RsTXaoHGM8chVpcjvFMfH0YbXIpS2qmdgzgSam5UYRHya7G6IogjCR6fMlcpKSn46quvMHr0aPz222+QJAmbN2/Grl27kJWVhc8//xzt2rXz91iJiIiIfFL03SeujY5VAU0GCFq98ryggmQxKZq8/W18zjt3I3fJfFjKPC+jCFX29Vb69j1aZbU38p2iqIXgU5jR7Pk8GTIpKQnPPvssnnnmGRQXF8NqtSIhIQFqtdqf4yMiIiJqNEvJGZc20VwbOKmj4yEIAtre9CxOf/CgrVESYSkrUN7kRXDluC7LUl4ETUyib4MOEnvmyjELQeQNXXIH+XXa1Y8GcSTB0+iVZoIgICEhwR9jISIiIgoIt5XLRNseV2FtuyJu0OUAAH27buj8wOc49p/pAIDKv7crbnFeg+WO1VA7Hcpe3r05sFaXo3TnKlirywEwuKKGE9QapFx+D8xnT0HfDKfE+oNPwdWoUaO8um7z5s2+dE9ERETkV6oI18IM9uIUyRPnQKUNk9vdVTlThUVANFZ5VS1QsdbEoWhGqDu7+g1UHfxZPmalQPJFVI+BQI+BwR5G0PgUXCUmJrrMwbVarSgoKEBeXh46duyICy64wC8DJCIiImosd1kYexZKUNW/NkSlj7IFV15krkp/WevwjOBVTJMkCWe+eh6CICDlsrsgqOpeuuEYWAGAOiImkMMjapF8Cq6++OILj+d+/fVX/Otf/8Lo0aN9HhQRERGRP0kmo2ubfc2Vqv6PQ/bgrL5gyVJWgPLfNtQ+w4tgLFCsFSWoOrATAFB9ZA8A29qysNR/KK4r27UOJdtXuNyvjooP9BCJWhy/l/HIzMzE1VdfjVdeecXfXRMRERH5RDQbXBsl25S9+jI6AKDSR9puqSdYMpw+pHyEU7XBpmSv+gcA5Xt/QN4XzyDnvftdritY9zYspWdd2jUMrogaLCA1Etu2bYvDhw8HomsiIiKiBpEsZlTu+8njeXdrrPQdeyuOVfoIua+GyPvsaRR992mD7vEXySG4qty7taZRhNlN5UR3tIltAzEs97wIcImaA78HV1VVVVi2bBmSk5P93TURERFRg5Xu+kZ+HT/8atcL3HywTxhxneJYHW5bf1TftEB30w9Lflrq8XpD9gGc+eoFt5mjxhJNbrJ1AHKXPFHvvbrUf0DnsMlyoLmt5kjUDPm05uqqq65y224ymXDixAlUVVXhzjvvbNTAiIiIiPzBmHtEfq3v0NMWTNWUYQcAwc0enSpdbfVAdWQc9B16ovz3zfVOC5TcTT+Ebe8od0U1cpfMh2QxwVJWgHYz/lPv1yI/RxJhOLkPYWldoNLp3V7jOC3Qkbs9v5w1ZCz+kDr9QeR98R8kjbmlSZ9L5G8+BVf5+flu29VqNbp164aJEyfi6qvd/GaIiIiIqInZs04AoImKg6BSQ3IMrtwUtFA5lCHXd+pdG8DUE1x5yhaZi88gLLWzS7t9TZbx9CFYygqgiUmqs3+7ky/PhLWyBPr2PdD2hqfdXiN5CK4AwFpZispDv9rKZjtJnniHV+vQ/Cm8Y290uucjCEJAVqwQNRmfgqtvv/3W3+MgIiIiCgh1eO0eV+rIeECtARwLTbjLXDneo4+y3YP611yJZtdpgQBgLslzG1w5KtjwHlKn3uf+/uI8qCNjodKFw1JRDGtlCQDAcOpvlP76DWIzL3Udi4dADwCKty5F2a9rUb57g6K93a0LEdamU53jDBQGVtQS8F1MRERELVvNPlbq6ESowsKdsjKC2w/1gsOmwhAEeU1QvWuuPEwLtFaUuG3XpXSUX5vPnnJ7TfWJv3DqjX8hf+WrAACxqlxxvnD9O+7HUkeWrWzXOgCAMbe2AFny5DuDFlgRtRReZa7uvvtunzpfuHChT/cRERER+Ys9IIrsdgEAp9LrbrJWACAIguMRBI1G0Zcza3U5yn5dB5OHAEk0VLofm+P0RMeAzkHR5o8AQN6zqvwP72YQ1bk+rKYMvaPwDr286peIPPMquFqzZk2DOxYEgcEVERERBZ09yBA0tuyTY+l1d+utnOnTuzlkrtwHLKc/fAjmwtPysToyFtbKUvlYNFS4vc9x6p6nPbEcC1NYDZUo3blKeYGggmQxy19f7cUN28BY0OoadD0RufIquNq/f3+gx0FEREQUEPagRS737RhcechcAUD6zP/CkHMAkT2HwHTmWE1f7gMWx8AKAPTte6Jy/3b52FrtGlxJkgTJq+Cqdh2XMeeg/Fqlj4IkWiCZDDAX57mUTq+vsqEzT1UHich7XHNFRERELZo9IJIzV47TAuuoiqdL6YCYflkQ6llzJboJisI79VFe45C5kixmnP7oEZx8ZZai3VJ6FnmfPwNJkmzXSZKteEVFsXzN2dWvy69Tpz0AbUI7AK7BnW2sDcxcca8pokbzqVogAOzbtw9bt25FZWWl/EMAACwWCyorK7Fjxw6sX7/eL4MkIiIi8pVkrclcaWzT3hyzVaKhyqs+7IGZu+DK3QbAEd0vRJuYRFQd/AXlezYp1lxVn9wHw6m/3T6n6vAuiFVlUEfGomDNmyj/fbPivD3Qiuo1FPr2PaBLbAtT3hGYi3Jc+pJE1+BKpY+UxxLZczAq9/3k6UsmIh/4FFxt2rQJc+fOhSjaFkMKgiAHWIIgQKVSoWfPnv4bJREREZGPKv74zvaipkiFoHWY/uYmAHGnrjVXlmLXTXlV+khEds2EoNbWBFcOGari3DqfZa0qg2g2ugRWjjTxbQAA2qR0AIAx76jLNfay8eGdz0X1sT8AAOqIWDm40sa1gaDReZyOSEQN51Nw9c477yA+Ph4LFiyA1WrFP//5TyxduhQmkwkfffQRvv32Wzz11FMN7tdqtWLLli3YunUrCgsLERMTg759+2LSpEnQ6z3PA961axfWrl2LM2fOIC4uDiNGjMCoUaN8+dKIiIioBXHcd0pVE1TZM1gAkHL5PV71IxfBsFogSZKimqC5RBlcCRodVDXPUOsjAQCm/JPyfcbcoy7XOwY41qpSVPz5veIaXZvOMBflyqXetXG24Cq8Y28UAzCcdJMJqwkEw9p1h6DWovrkPoR36gNzkW0KoToyFtqkdJjcBGZE5BufgqsDBw7glltuwZAhQyCKInQ6HXJzc5GVlYV+/frhqquuwmuvvYbXXnutQf2uWLECmzdvxtixY9G1a1fk5eVh1apVOHr0KO677z6oVK5LxH777Te8/fbbGDZsGC6//HLs378fX375JSRJwujRo3358oiIiKiFEKvK5NdRvYfa2oy1UwEjMwZ41Y9jhUFYLYBDZT5reZHyWofCEKrwKPn1sWemInniHag8+LPiek18KsxnT8rHxtwjKP9dWW5dMhugjoyBpcQWXKmj4gHY1oUBgLWyBKaCbEhmE4ynD8JSVgDRYgssBY0WbaY9CFgtKHcI2tRR8UiZ8m/kLn4csQMmefV9IKK6+RRcWSwWpKWlAQBUKhU6dOiA/fv3IyvLtuhz3Lhx+OCDDxrUp8lkwubNm5GVlYVJk2x/wXv06IGoqCi88847OHjwIDIyMlzuW758Oc4991xcc801AIBevXrBYrFgzZo1GD58OLRaLs4kIiJqrezl0G0bCEcAUO45pdzPqg4OwZRkVZY9tzoEcLY+a38ZrA6PVpw7u+pVl66jzx2Bos0fyscVe7e6XGOtLIU6OqG235rgShUWAVVEDMSqMmQvutPt0AW1xvZ1arRQR8bW9hEZC11iO3S80/0mxETUcD5VC0xLS0NOTu3CyQ4dOuDAgQPycVhYGIqKitzd6lFlZSWGDBmC/v37K9pTU1MBACUlJS73FBQU4MyZMzj//PMV7f3790dVVRWOHDnSoDEQERFRy2KtqgmuImLkNtHofkPfujhmruxrmeRnVJd7vFalj0REF+VnG2cRXZSfY9xN05NEqyKI00Qn1r6uCbQ8cawCKJdrF1RypUEi8h+fgqvhw4djyZIl2LRpE0RRRL9+/bBt2zYcOXIEJpMJq1evloMib8XHx+Oaa65Bhw4dFO179uwBALRr5/oDIC8vDwDQpk0bRXtKSgoAIDe37gWjRERE1LLZN+lV6SPktshuFwGwrWPyliCo5LLtjkUtREMlqg7sVD7TYZ0XALSZeq9Lf6rwaAgaHcLP6QdtovsgR5vY1qFTEYmjbgAARJ07AuqI2oyYqmZdl8exOwR72vhUpN/2MtJvexma6LqDMiJqOJ+mBc6ePRs//vgj7rjjDmzfvh3Tpk3Du+++i4kTJ0Kn08FoNOLee11/kDTUkSNHsH79evTp0wft27d3OV9dbduxPDw8XNFuL35hMBhc7iEiIqLWw1463THASBx9I3RtOiGyx8CGdaZSA6JVUY69eNsy+bW9MEVUr6GK2wS1FimX3YX85S/KbdrEtki76lEIGtuUPVV4NESnDJjjhsWSaEX0uSMQfe4I12GFeR9cAYCupsIgEfmfV8HV3Llzcdlll2HYsGFQq9VISEjAypUr8e233yIuLg4A8Nlnn+Gtt95CaWkpLr74YkybNq1RAztw4ADeeOMNJCUl4aabbnJ7jeP+Wu54PY/aDavVirNnXfetCAaj0Shn6YiChe9DCja+B8kXlpplCkazVfn+aX8+qiuMQEUD3lO6CMBiQv7JI1DXJKeqD+6ST+unPQHryT9h7ny+y3vVUl6hODZLKuQXl9Z2PeFuWE/8AfPPtcGaxeTwS2JJ9Pj+N0p1T0QqM0mo5N+dFoM/C5teUlISNBrvclJeXbVp0yZs3LgR8fHxGD9+PCZPnozevXtj7Nix8jUdO3bEs88+69uInWzbtg1LlixBWloa5s6di6ioKLfX2TNWzhkq+7FzRqsh1Gp1g6c2BkpeXl7IjIVaL74PKdj4HiRflOVEoACAPiKy0e+f44npEKtKEGUuQ2xqKgyn9qOq8JR8Pq1zN6BzN7f3VlXmwvHjsD4qRjme1FSgWx8g61oc/b8rAAAq0QIRjpe4H39BXCLKnNrSrn8KZ1e9BslqQdp5Q6DShjXgK6VQxp+Foc2r4OqHH37AmjVrsGbNGnz88cdYvHgxzjnnHEyePBmTJk1yWfPUGCtXrsSaNWvQs2dP3HbbbXXub2V/Y+Xn56NTp05ye35+vuI8ERERtU6SaAXgOjXOF6roRIgArBUlAIDKQ7/I5+IGXV7nvY7VBQF4Few4loyvi+P6KwBIuvQ2hHfoifRbFwKSyMCKqAl5VdAiKSkJN954I7744gts3LgRc+fOhSAIWLhwIUaOHIkZM2bg66+/ltdA+WrdunVYs2YNBg4ciDlz5tQZWAFAcnIykpOTsXv3bkX7rl27EBERgc6dvV+oSkRERC2PvfiEP4Ir6GwzYkSDbYqfWF071U902ATYHceNiwFA0Hr+jJM07p8AgIRRNyC6XxYAIHbAZI/Xqx0qB6r0UYg5/xLb67DweotdEJF/NfgnTfv27TF79mzMnj0bBw4cwKpVq7B27Vrcf//9eOKJJ5CVlYUpU6Zg4MCGLRI9c+YMvv76a6SmpmLo0KE4ceKE4nxycjI0Gg1yc3ORnJyM6Gjbb2kmTJiA999/Hx9//DH69euHAwcOYMuWLbjiiiug0+ncPYqIiIhaCTm4UjU+uBJ0Nftk1WSULGWFtc8x1xNcqZWZK43DnlXOYvplIeKc86GOigMkEdHnjkBY2y4er9fEJNU+R8PPPkTB1KifNN27d0f37t1xzz33YNeuXVi3bh2+/fZbrFy5EqmpqdiyZYvXfe3ZsweiaFus+dxzz7mcv/7665GcnIwXX3wRN954IwYNGgQAGDBgAKxWK9avX48dO3YgISEB06ZNw8iRIxvzpREREVEL4M/MlRBmz1xVQjRWo/rob/I5x1Lvbu91mhaoia97SYUmxp6NUkOf3r3Oa8PadJJfWyuK67yWiALLDzlym/79+0OlUkGv1+OLL75ocBWTMWPGYMyYMfVet2jRIpe2wYMHY/DgwQ16HhEREbUC9j2p/DIt0BZAWQ0VKPr+k9p2lRpxA6fUeatzRkkb57/16urIWMQNuhwl25YhbvAVfuuXiBqu0T9pdu/ejW+++QYbNmxAfn4+wsPDMWbMGEyaNMkf4yMiIiLymSTaM1fqRvcl1OwnZa0sheHk33J7u5v+A3V4tKfbADhmomqO/RhcAUD8xVcjqtcQaJM7+LVfImoYn4KrPXv24JtvvsH69etx5swZqFQqDBo0CPfeey9Gjx5dbyEKIiIioqbg1zVXkfEAAGt5EYS4FLldFVb/1i+CSg1tcnuYz9pKt6sjYxs9HkX/ggq6lI5+7ZOIGs7rnzR//PGHHFDl5uZCkiT06NEDN910EyZMmICkpKT6OyEiIiJqQrVrrrT1XFk/IcIWEEkWk1yOHQBUYXWvt7JLn/lflPz4JbQJaRAEodHjIaLQ41VwNXLkSDmgatOmDW655RZMnjwZXbt2DfT4iIiIiHxnte1z5Y81V45FKezl2IHaQhf13i8IiB82rdHjIKLQ5dVPmuLiYkyZMgWTJk3CgAED+NsWIiIiahb8uebKncgeA6Fi+XMiquFVcLV9+3auoyIiIqJmQ7SYULDmTVT89QMA/0wLdCfm/PorHRNR66Hy5iIGVkRERNSclO/ZLAdWAKAKjwrIcwQtPyMRUS2vgisiIiKi5kSsLlccq/WBCa5UurCA9EtEzRODKyIiImpxnDftZeaKiJoCgysiIiJqeQTlRxyVnzJXYW2VlZJVWmauiKgWgysiIiJqcawVRYpjTXSCX/pNnf6w4lil926PKyJqHXze9MFiseDTTz/Fxo0bkZOTA61Wi7S0NIwcORJXXXUVtNrAVOUhIiIiqk/pzlWKY5XOP9P31BHRiuNAVSEkoubJp+DKYDDglltuwa5duxAVFYX27dtDFEX88ccf2L59O1avXo2PP/4YOh33fSAiIqLgShwzMyD9MrAiImc+BVdvvPEGdu3ahXvuuQc33nijnKUym8346KOP8MILL+B///sf5syZ49fBEhEREXlD0IVDMlUjfdZL0CW3D8gzAlUkg4iaL5/WXK1duxZTpkzBrbfeqpj+p9Vqccstt2Dy5MlYtWpVHT0QERERBZIEABDUPq+A8MheHCOia6bf+yai5s2n4CovLw/nnXeex/N9+/ZFbm6ur2MiIiIiahxRtP1f5f/aXW1v/D/ED7sKiaNu9HvfRNS8+fTrnKSkJBw8eNDj+QMHDiA+Pt7nQRERERE1hiTZgitBpfZ737qkdOiGXun3fomo+fPp1zmjR4/GF198gTVr1ricW716NZYuXYrRo0c3enBEREREPrFnrgTuOkNETcenzNWdd96J7du345577sFLL72Ezp07Q5IkHDt2DDk5OejQoQPmzp3r77ESERER1UuSJEBicEVETc+nnzjR0dH47LPPMHPmTOh0OuzcuRM7d+6ETqfDrbfeiqVLlyI2NtbfYyUiIiKqnz2wQmCmBRIReeJzCZ3o6GjcdddduOuuu/w5HiIiIqLGcQiuAlHQgojIE6+Cq2PHjiElJQWRkZHysTc6d+7s+8iIiIiIfCCJDpkrTgskoibkVXA1btw4PPfcc5g4cSIA4NJLL4UgCPXe9/fffzdudEREREQNJTJzRUTB4VVw9a9//Qvdu3dXHHsTXBERERE1NUmx5orBFRE1Ha+Cqzlz5iiO77jjjoAMhoiIiKjRRGvta04LJKImxJ84RERE1KI4rrlicEVETcmrzNWQIUMa3LEgCPjxxx8bfB8RERFRozjsccVlDETUlLwKrlj1j4iIiJoNe3DF9VZE1MS8Cq4+/vjjQI+DiIiIyC+kmjVXLMNORE3N502EAcBsNmPPnj3IycmBVqtFWloa+vbtC7Wau6ETERFRkNjXXKn4eYSImpbPwdW3336Lxx9/HAUFBZAkCYBtnVVCQgLmz5+PrKwsvw2SiIiIyFv2Uuwsw05ETc2n4OrXX3/F3LlzkZiYiHnz5uGcc86BJEk4cuQIlixZgnnz5uHjjz9Gv379/D1eIiIiorqJtQUtiIiakk/B1euvv460tDQsW7YM0dHRcvvo0aNxzTXX4IorrsBbb72FRYsW+W2gRERERN6Q11xxWiARNTGffqXz+++/48orr1QEVnbR0dGYOnUq9uzZ09ixERERETWcxMwVEQWHTz91JEmCVqv1eF6j0cBkMvk8KCIiIiKfiSzFTkTB4dNPnZ49e2LFihVuAyiTyYQVK1YgIyOj0YMjIiIiaigWtCCiYPFpzdWsWbNw2223Ydq0aZgxY4a8yfDRo0fx/vvv49ChQ3j99df9OlAiIiIir7CgBREFiU/B1fDhw/HEE09gwYIFeOCBB+R2SZIQHh6ORx55BCNHjvTbIImIiIi8JVqMAACVVhfkkRBRa+NVcLV582ace+65SE5OltumT5+OsWPHYtu2bcjOzoYkSUhPT8fgwYMRGxsbsAETEREReSJZLbCUngUACNrwII+GiFobr4KrBx54APfffz+mTp0KALjhhhswe/ZsDBw4EJdeemlAB0hERETkrTPLX0TVgZ0AAFWYPsijIaLWxqvJyBaLBX///bd8/PPPP6OwsDBggyIiIiLyhT2wAgCVjpkrImpaXmWuhg4diiVLlmD58uWIiIgAADz55JP4z3/+4/EeQRDw448/+meURERERA0kMLgioibmVXD1zDPPoF27djh48CBMJhMKCwuRlJSExMTEQI+PiIiIyCuSJCmOVTpOCySipuVVcBUVFYX7779fPs7IyMDs2bMxceLEgA2MiIiIqCEki3L/TU00fwlMRE3Lpw0gnn32WfTs2dPj+SNHjmDRokU+D4qIiIiooURjteI4qvewII2EiForn4Krhx56SFHgwtmOHTu4iTARERE1KcmkDK40McxcEVHT8mpa4KlTp3DvvffKx5Ik4dVXX8XixYtdrhVFEYcPH1bsiUVEREQUaI7TAtvfzl/yElHT8yq4at++Pbp164atW7cCsFUCLCsrg9lsdrlWrVaja9euuOOOOxo1sOLiYjz55JOYNWsWevToUee18+bNQ1VVlUv7c889xw2NiYiIWglJFAEA6qh4aONTgzwaImqNvAquAFvpdbuMjAw89NBDAStoUVRUhFdeecVtwOSsoKAAVVVVmD59Ojp16qQ4FxUVFZDxERERUQgSrbb/q9TBHQcRtVpeB1eOpk2bhpiYGH+PBaIoYseOHVi6dKnX92RnZwMA+vfvzywVERFRKyZJtsyVIPi0pJyIqNF8+umzYsUKnDx50t9jQU5ODpYsWYIBAwZgxowZXt1z6tQpREdHM7AiIiJq7WqCK6gYXBFRcPiUuUpLS0NeXp6/x4KEhAQ8/fTTiI+Px4EDB7y659SpUwgPD8cbb7yBAwcOQJIk9OnTB9OmTWPARURE1IrY11wxc0VEweJTcDVv3jw88sgjKCgowEUXXYTExESo1a7zm4cMGdKgfiMjIxEZGdmge7Kzs1FRUYEhQ4YgKysLubm5WLVqFV544QU8/PDD0Ou5OzsREVGrIK+5YnBFRMHhU3D173//GwDw9ddf4+uvv4YgCIrzkiRBEIQ698Lyl5tvvhl6vR7p6ekAgK5du6Jt27Z4/vnnsX37dowYMcKnfq1WK86ePevPofrMaDQGJFNI1BB8H1Kw8T1IdbGeOQrx7HEAgMUqBuS9wvcghQK+D5teUlISNBrvwiafgqtnn33Wl9sCokuXLm7bwsPD5WIXvlCr1UhNDY0yrnl5eSEzFmq9+D6kYON7kDwxFZ5G9uqF8rFWFxaQ9wrfgxQK+D4MbT4FV5dddpm/x+GTiooK7NmzB126dFG8yURRhMViYSl2IiKiVqD66G/KBq65IqIg8Sm4sjtw4AA2btyInJwcaLVapKWlYcSIEcjIyPDX+OqkVquxZMkSDBw4EDfccIPc/scff8BsNqN79+5NMg4iIiIKHkt5keJY4JorIgoSn4Or559/Hu+99x4kSVK0v/LKK7jhhhvw4IMPNnpwzsxmM06dOoX4+HjEx8cjPDwcWVlZ2LBhAyIjI9GzZ0/k5ORg1apV6NOnD3r27On3MRAREVFosZQ6rZFm5oqIgsSn4Grp0qV49913cfHFF2P27Nk455xzIIoijhw5gkWLFuGjjz5Cjx49MGXKFL8OtrS0FAsWLMCECRMwceJEAMCUKVMQFxeHH374AVu2bEFUVBSGDx+OCRMm+PXZREREFJrMBTmKY2auiChYBMk59eSFKVOmIDo6Gh9//LHLOUmScMMNN8BgMODLL7/0yyBbOy5cpFDA9yEFG9+D5I5oNuL489fVbiAMQN+xF9pe96Tfn8X3IIUCvg9Dm0+/2jl69CjGjBnj9pwgCBgzZgwOHz7cqIERERER1cdaUawIrABuIkxEwePTT5/w8HCUlJR4PF9UVASdTufrmIiIiIi8Yq0qc23ktEAiChKffvpcdNFFWLx4sdt9pE6dOoVPPvkEF1xwQaMHR0RERFSXygM7XRuZuSKiIPGpoMWdd96JqVOnYsKECRg/fjw6d+4MSZJw9OhRfPPNNxAEAXfeeae/x0pERESkUPbzGpc2TgskomDxKbg655xzsHjxYjz11FP46quvFOf69u2LRx55BF27dvXLAImIiIg8EXR6SNVmqCPjYK0ssTWq1EEdExG1Xj7vc9WrVy989tlnKCwsRE5ODiRJQnp6OhITE/05PiIiIiKP1OHREKvLEdlzEMp+WQuApdiJKHgaFFwVFBRgz549sFgs6NWrF9q3b4/ExEQGVERERBQUorEKAKCOjKtt5LRAIgoSr4IrSZKwYMECLF68GFarVW4fM2YMnnnmGURERARsgERERESeyMFVRGxtIzNXRBQkXgVXH3/8MT744AOce+65uPTSS6FSqfDTTz9h3bp1CA8Px7PPPhvocRIREREpSFYLJIsJAKCOrA2uLCVngzUkImrlvAquli9fjsGDB+Ptt9+Gqua3QTfeeCPmz5+PpUuX4vHHH4derw/oQImIiIgcWcoLAQCCWqsIrow5B4I1JCJq5bzKmx8/fhxZWVlyYGU3depUWCwWHD16NCCDIyIiIvLEXGDbb1OTkApB5XONLiIiv/EquDIYDG7XVaWlpQEAysvL/TsqIiIionpU7rdtIByW+g8AUnAHQ0QEL4MrSZIgCILrzTWZLFEU/TsqIiIionpYymxrq8I79YEu9R8ISzsHAJB69WPBHBYRtWLMoRMREVGzJJoMAABVWAQEQUC7m58L8oiIqLXzOrgqKSnB6dOnFW2lpaUAgKKiIpdzANC2bdtGDo+IiIjIPdFUDQBQ6cKDPBIiIhuvg6tnnnkGzzzzjNtz99xzj0ubIAjYt2+f7yMjIiIiqoNktAVXAoMrIgoRXgVXl112WaDHQUREROS16uN/wlJWAABQ6bgdDBGFBq+CK24STERERKFCkiTkLpkvH6vCmLkiotDgVbVAIiIiolAhGqsUxyp9VJBGQkSkxOCKiIiImpWct+9SHHNaIBGFCgZXRERE1GyIxip5rRXAYhZEFFoYXBEREVGzYS7KVRwLGm2QRkJE5IrBFRERETUb1spSxbGg0QVpJERErhhcERERUbMhWcyK44SLrwnSSIiIXHm9iTARERFRsJjOnoQqPAaS1SS3JU+8A9F9hgdxVERESgyuiIiIKKSZi/OQ/b95gEqD5HG3AQDCzzkf0edeHNyBERE54bRAIiIiCghJkiBZzfVfWA/Dqb9tL0SLPC2QhSyIKBQxuCIiIqKAOLN0AU68MgvW6vJG9SOJVvm11VAJgMEVEYUmBldERETkd6KxGlUHf4FYVYbqo3sa1Zdkrl1nZa0oAgAIalYJJKLQwzVXRERE5Hflf2yRX4s12SZflP68GoUb35ePLeW24ErFzBURhSBmroiIiMjvTPkn5NfVJ/c1+H5JEmE1VCoCKwCwVpbYXjC4IqIQxOCKiIiI/Krst40o37NJPq7c9xMkSfT6fslqRs57D+DEwhtcztmzYMxcEVEoYnBFREREjSZJEoy5R1D+x3coWPuWy/ny3za5ucu9gvXvwZR3xO05c0G27YWawRURhR6uuSIiIqJGq9y/HfnLFno8X3V4N2LOv8Srvsp/21DvNSqd3uuxERE1FWauiIiIqNHKfv3GpS38nH6I6jUUAKCOiPa6LyEsot5rVLpw7wdHRNREGFwRERFRo4iGSpjs0/VqxA6cgrSrHoG+Q08AgLXK+72uVBpbmfWwdt2QMvnfbq8RmLkiohDEaYFERETUKNnv3QexqkzRJtSsiVKF2zJWlrICr/qSJAnW6goAQJvL74a1stTtdSotgysiCj3MXBEREZHPrIZKWIrzXNqFmmp+upSOAADTmWMwF+XW259kMgCiBYAtMNPEJru9jmuuiCgUMbgiIiIin1lK8t222zNXusS2EGqyTKfenAPRbKyzP2u1LQMmaHRQacOgjohx33/N1EEiolDC4IqIiIh85mm6n6CuXXkgmQ3y6xMv3oSc9x+ApazQ7X327JZKHyW3JWbNcLlOpY/0abxERIHE4IqIiIh8ZnVaayVz2DQ4ftj02maLCcbTh1C0ZbHLLaKxGnmfPmXrt6JIbo+9cAJSrrhHPk6eOAe65PaNHToRkd+xoAURERH5TDJVu213nP4XN+hy6FL/gTNfPCu3OVcXBICSnSvl187VACO7XYiY/mMR1q4bovsMb+ywiYgCgpkrIiIi8plotAVXgi4cKZffLbdLZpP8WlBrENGlv+I+d/tUGY7/Kb9Ov+V5xTlBpUbS2JkMrIgopDG4IiIiIp9Zq2yl0mP6ZSGqxyC5XbKYFNcJgqA4lqwWl76MuUcAAG1v+g+0CW39PVQiooBjcEVEREQ+MeYeRdmv3wAAVGG2TJS+fQ8AQJSbDJPWYZ2UMecAJEmSjyWLWQ7ItIkMrIioeeKaKyIiIvJJwfp35NeqsAgAQNq182GtKocmOt7l+rbXPoHSX9ai5KelAIDqo3sQcU4/AIBorKrti3tYEVEzxeCKiIiIfCJoa/easm8WLKg1bgMrAFBHxiKqz/Da4OrY71BHxMJUcBLGnEO2+3XhEFTqAI+ciCgwQja4Ki4uxpNPPolZs2ahR48edV574MABLF++HDk5OYiMjMSgQYMwfvx4qNX84UxERBQoksUMAIjo0h/hnfp4dY/aYX8qU/5J5Oy816lTCUREzVVIBldFRUV45ZVXUFVVVe+1x44dwyuvvIK+fftiwoQJyM7OxsqVK1FdXY3p06fXez8RERH5RjRUAABiL5ro9T3qyFj5dfWx313OO244TETU3IRUcCWKInbs2IGlS5d6fc/KlSuRlpaGmTNnQhAE9O7dGxqNBl999RXGjBmDuLi4wA2YiIioBRCNVch5/wHoO/RC8rjbvL+v2hZcqRyyUd6IPm80yvdsatA9RETNQUhVC8zJycGSJUswYMAAzJgxo97rzWYzDh48iH79+ilKvPbv3x+iKGLv3r2BHC4REVGLULF3K8yFOSj/bUOD7hMNlQAAVXhUg+4TtGEez4W169agvoiIQklIBVcJCQl4+umnMW3aNOh0unqvLygogMViQZs2bRTt8fHx0Gq1yM3NDdRQiYgoRBjPHEfup0/CePpwsIfSbBnPHJNfi6Zq+bW5JB+i035V8nVmIySrbc2VWt+w4MpaWeK2ParPcKRMmdegvoiIQklITQuMjIxEZKT3Uwuqq23/AOj1riVb9Xo9DAbO2yYiaunyPn0S1spSnD75Nzrf/2mwh9MsGU7uk19X7P0JMf1Gw3Dqb5z+6BEAQPvZr8FaVYb8r19G4qgbEZlxkTwlEIIKgi68Qc+zFJ9RHId3PhexA6cgonPfxn0hRERBFlLBVUNJ9VQUct4NviGsVivOnj3r8/3+ZDQakZeXF+xhUCvH9yEFm6f3oLWyFAAgWUx8j/pAkkRYqsrl4+J9O1CV1huGTR/LbafefwCCWgupshhnvnoO4dc9B6nm+w5dOM6cOePcbZ3ETucDubZMo6bvWAiZE1EGoCzE//z4c5BCAd+HTS8pKQkajXdhU7MOrsLDbb8pMxqNLucMBoPbjJa31Go1UlNTfb7fn/Ly8kJmLNR68X1IwebpPXjU4TXfow0jWczIfucuSFWltY2FJ5CamopcvR7yBEFDBRx/nRlx9iCKf/wCAKCNjGnw911KmQrDP3pCpQuHLrVzs9nXij8HKRTwfRjamnVwlZycDJVKhfz8fEV7cXExzGYz0tLSgjQyIiKi0GfMPQJz4WlFm7W8CKKhEtbKMo/3Fa5/p1HPFVRqr/fFIiJqTkKqoEVDabVadOvWDb/99htEUZTbd+3aBZVKhYyMjCCOjoiIKMQ5TZ+3r50ynT0Jk0ORi7qEpffw+7CIiJqrZhVcmc1mHD16FMXFxXLb+PHjcfLkSSxatAh//vkn1q1bh2XLlmH48OFISEgI4miJiIhCm2NlQAAIa9sFAFD682qv7o/MGIDEkdf5fVxERM1VswquSktLsWDBAmzdulVu69atG2bPno3CwkK89dZb+O677zB27FhMmzYtiCMlIiIKbdbKUlTs3apo06V0BABU7t9ha1A5rx5QZrpSpsyDOjI2UEMkImp2QnbNVffu3bFo0SJFW1JSkksbAPTt2xd9+7J8KxERkbcKNryLyn0/Kdr0bbvCcaVVVO8hqPjjOwCAKiIG4R17ofLv7fJ5QR2yHyOIiIKCPxWJiIhaIccgCQDa3fw8tAlpELRhkMy2Krwqh82B9ekZEDS6Jh0jEVFz06ymBRIREVHjmQpPA1JtIajUqx9DWNo/oAoLR0z/sXK7Wh+F5An/QljaOUgacysEtVY+F37O+U06ZiKi5oCZKyIiajGqj/0BfYeenK5Wj+xFd8qv29/+OrTxtXvmOK6h0sQkIrrvSET3HQkAisxV3MApgR8oEVEzw8wVERE1K5IkwZR/EpLFXNNSW2Qh95MnULJjZXAG1pw4ZK1U4dGKU46Bqb5DT+U5TW3mioUsiIhcMbgiIqJmpfLvbch+ex7OfPU8AEDQKtcBlfz4RTCG1WypwsIVx/oOvQAA2qR0RUYLUAZXKn1k4AdHRNTMcN4EERE1K2W/fgMAqDq8CwAgiVbFeedMDNVNEJS/Zw1r0wnpM/8LTWySy7UqbZj8Wu1Q7IKIiGyYuSIiomZFFRYhv5YkEbBaFOetFUWwlNs2mzdk74fx9OEmHV9LoEvpoPg+2wkOwZVjFouIiGwYXBERUbPiOB2tYG3t3odJl94GdVQ8AMBaUQzRWIXTHz6MnPfvh2Q1u/TTWokWk/w6rF33Bt2rb9+z/ouIiFoxBldERBSSrFXlKP1lDaxVZYp2QaeXX5fv2SS/jj5vlBx4icZKWKsr5HPmkrMBHm3zIRqq5Ndp1zzWoHvDUjsj7dr5aD/7NX8Pi4ioReCaKyIiCkmFm95HxZ/fo3DDe4jomglp6I0AAMlkcL1YpYagUkMVVhNcGaogmarl05aiXOgS2zbJuEOdaKwEYJteqXIIVL0V3qmPv4dERNRiMHNFREQhqeLP7+XXVYd+hZi9z9a+d6vLtfb9l1R62zoh0VgJ0VgbXBX98DkMOYcCOdxmQzTUBFes9kdE5HcMroiIKCSFpZ2jOBYLs22BgcMeTXYqrT24sgUM1upyWKvL5fOmvCPIXTJf0dZaycFVGIMrIiJ/Y3BFREQhSZIk5XF1GSwVxfJx2xuell+roxIAAGEpHQEAlQd+xpkv/6O832yAMedgoIbbLJhLzqBoyxIAtVk+IiLyHwZXREQUkuwZlsgeAwEAUnUFrJWlAABtQltoYlNc7onqPRwQVDBm769tVNUuL27tmauc9+6H6cwxAIAmxnUfKyIiahwGV0REFJLsmwNrohNtx4ZyWCtLAADqyFhoYhIR0f0iAEBE10zbtTGJiD53hKKf9v98GZE9BwMARIcKgq2R6BBcauPTgjgSIqKWidUCiYgoNNVsDqyuybBIVaUw5Z8AAGhqAoM2l98Nw8l9CGvXTb4tbvDlKP99MwAgrG1XaONToQ6PtnVZ1TozV5UHdkKblK5oC2vXNUijISJquRhcERFRSJJEW3ClS25vOy47C2PeUQBAWNo/AACCSu1SGlwbn+rSl8oeXFWXuZxr6aqP/4kzS59zaQ/v1DsIoyEiatk4LZCIiEKSZLVNC9TGpdhKrUsiDNkHbG1u1ls5iht0GQABCSOvBwBoom0FL0y5R1wKZbR09u+ZM0GtbeKREBG1fAyuiIgoNNVMC4RaA3VkLABAMlbZmmqCJU/iL74WHe/6AOEdewGoLd5gzD2Csl/WBGjAIcpN6XoiIgoMBldERBSS7AUtBJUWltKztScEFTSxdVe6EwQB6vAo+VgTmyy/Ltz4fqvKXrWmr5WIKNgYXBERUdBJFjPylj6Ho/93BY49fx3MxXlyxkVQqxXXJo25RS5Q4S1tYlvF8bFnpqLy4C+NG3RzITJzRUTUVBhcERFRUEmiFXlfPIOqAzttx6ZqVB3eJZ8X1BoI2jAAgCY+FTH9xzb4GYJKjaRx/1S0nfnyP/K+WS2ZMfeQS1v6P18JwkiIiFo+BldERBRUZ5Y+h+pjfyjaCje8V3ugUiPt2vlQd+qHtGse9/k5Mf2y0P5fbyraynZv8Lm/5qL66O+KYyEsArrEdkEaDRFRy8bgioiIgka0mFB16FcAgCbOfQVAQa2Bvl03hI26FVoP13hLG5eC8M7nyscVe39sVH+hTjQbXdpUGl0QRkJE1DowuCIioqAxF56WX7e9/mm0n/2a60WCf/+pSrvmcaTP+q/8fNFU7df+Q4UkWlGw5k2XdoHBFRFRwHATYSIiChpLyRkAQFjbrtDEJAIA1FHxsFYUy9cIguD35+qSO0AdlQBrRREMOQcR0bmv358RTNXH/0TukvluzwlaBldERIHCzBUREQWNZDYBAFQ6vdwmGiqb5NlhqZ0BAHmfPInCzR+2qJLlRd994vEcM1dERIHD4IqIiILGvibIXg0QAMLadW2SZ0dmDJBfl+5YieI6ApLmRh0V79RSm/1TRzSsjD0REXmPwRUREQWNZLFlrhyDq5RJd0JQawP+7Igu/RXHpT+vljcubu608amK45jzL5FfuwZeRETkLwyuiIgoaCR75sphqpomJhGd7v8UsRdNQvKkOwL2bHVkLJLG/RMJo2+0jcVigrkoN2DPayoVe390qYIY03+M/FrD4IqIKGBY0IKIiILGPi1Q5ZC5AmxFLBJrgp5AiumXBQCo3LcNxtOHYDx9CLqk9IA/N1DMpfnIX/GSS7sqIkZ+rY5KaMIRERG1LsxcERFRkzPmHkXxD1/IVQGDXWQhosv5AIDy378N6jgaw1R4Gqdem61o03fshXa3vAB1eO06K665IiIKHGauiIioyZ3+8CFIVrN8HOzy4FHnXoziHz6H4eTfEC2mZrnRbvmeTS5tkRkD5aqIUKkB0Qp9+x5NPDIiotaDwRURETUpyWpRBFYAIGjCPFzdNDQxyRB04ZBM1bCU5EM0VKBw04dIzJoBfbtuQR2bt9QOU//sBE1tYZAOc96CaKiEJiapKYdFRNSqcFogERE1KUtFkUubJjq4RRYEQYA2rg0AwJhzEKc/ehTGnIM48+WCoI6rIezr1xzLrisKhUQnQJfcvolHRUTUujC4IiKiJmWtKHFp0ya2a/qBOInsfhEAoGLfT4AkAgCslSWQrJZgDstrkrEKgK0Kop1j5oqIiAKPwRURETUpe7CiTWiLxDEzETfocoS1bZqNg+sS0f1CAIAhe7+ivWz3hmAMp8FEYzUAQB0ZJ7c1x7VjRETNGddcERFR07JngtQaxGaODe5YHOiS2gGCCpLJoGg3nNyH2AvGBWlU3hNNNZmrqFgg39Ym6MKDOCIiotaHmSsiImpSkmgFAAgqdZBHoiSotdDEJLq0OxffCFW1mava9WsqBldERE2KwRURETUp+7RAQR16kye08akubeaiXEiSFITRNExtcFW75kql0wdrOERErRKDKyIiajKSJMF09hSA0Ayu1M6ZK5UG5sIcmAtzgjOgBhBNrsEVpwUSETUtBldERNQkrFVlOPbMVBR/t8TWEILBlb5t7Z5WSeNmyxvwmvJPBGtIXrNXC3ScCsjMFRFR0wq9f9mIiKhFKv/ze8WxoAq9f4Kiz8+CJj4V6oho6Np0hjH3MIynD8GYcxBRPQcHe3h1kjNXEQ6ZK21wN2cmImptQu9fNiIiapGcq/AJ6tAqaAEAgqBCxD/6ysfhnfqg/LeNqD65L4ijqp8kSfKaq7B2XRGTOQ7qqDgIglDPnURE5E8MroiIqEnYqwTKQqxaoDu6lI4AAHNxnlzUovLADqi0ekSc0w8AULF/O3QJ7aBL6RC0cUpmo7zxsSosAkljbgnaWIiIWjMGV0RE1DScgyv7flchTBOXAkCAZKzC8QVXK8qyd37gcxhyDiL/qxcAAP94+KsgjbK2UiAEFacCEhEFEQtaEBFRk5BqMit29jVCoUyl0SGi+4UAXPe7Kt+zCcacg/KxaDY26dgc2TcQVoWFcyogEVEQhVzm6sCBA1i+fDlycnIQGRmJQYMGYfz48VDXMTd/3rx5qKqqcml/7rnnEBsb6+YOIiJqck6ZKznbEuKSLrkFJw/sdGkvWPc2Yi+aKB+bC3KQv+K/MBedRvo/X4Uusa3b/iRJQuX+HQhL+we0cW0aPT5D9n5YqysAcNNgIqJgC6ng6tixY3jllVfQt29fTJgwAdnZ2Vi5ciWqq6sxffp0t/cUFBSgqqoK06dPR6dOnRTnoqKimmDURETkDec1V9bK0iCNpGE0zntfOSjduUp+XfTdEpiLTgMAznz1PNrP+q/be8p+WYPCje8DANr/601o41J8HpvxzHGc/vBh+dhSVuBzX0RE1HghFVytXLkSaWlpmDlzJgRBQO/evaHRaPDVV19hzJgxiIuLc7knOzsbANC/f39mqYiIQpmonBZorSgK0kAaLiw9A8bs/dDEpyJl0lyc/vAhl2uqj+6RX5vPnoRktSg2SrZWlaFw04eo+PM7uS1/xUtod9MzPo/LePqwz/cSEZH/hcyaK7PZjIMHD6Jfv36K+eL9+/eHKIrYu3ev2/tOnTqF6OhoBlZERCHOOXMVN2RqkEbScIlZMxB9/iVoe8PTCGvXDYIXm/OefHUWRIsJgG2PrxP/naEIrADAmHOgcQNzWl8V0e2CxvVHRESNEjKZq4KCAlgsFrRpo5x/Hh8fD61Wi9zcXLf3nTp1CuHh4XjjjTdw4MABSJKEPn36YNq0aQy4iIhCSU1wFT/sKkR0OR+6Np2CO54G0LftAn3bLrUNQu3vJtOuewK5ix93ucdaWYqqQ7sQ1WMgyn5Z47Fvc2k+tLG+TQ0Ujcr1xnEDL/OpHyIi8o+QyVxVV9sWNuv1rr8N1Ov1MBgMLu2AbVpgaWkpzjnnHMyZMwdTp07FwYMH8cILL3i8h4iImp5UMy1Q0GgRlnYOhGawz5Un9n2k4oZOQ3jH3kgYfaPb60xnTwJQVkbUpXRC25v+A21iOwBA0beL5YIUDeUcXAkanU/9EBGRf4RM5sq+OaMnnkrL3nzzzdDr9UhPTwcAdO3aFW3btsXzzz+P7du3Y8SIET6Nx2q14uzZsz7d629GoxF5eXnBHga1cnwfUmMZq2wBRHllFQw+vJdC6j2YnAH9tCdhjEqwjanjhdBmlkCqKoVl33fyZWVH/4SxfT+YC08DEBB+7X8g6KNQAkBq0xUozEHlvp9Que8naM8fD22/cV4PQaouR/WPX8jHqpTOKBJ1EELle9QChdR7kFotvg+bXlJSEjQa78KmkAmuwsNt5WONRtd9QgwGg9uMFgB06dLFbVt4eLhc7MIXarUaqampPt/vT3l5eSEzFmq9+D6kxjoTFoZKADGxcYj14b0Ucu9B57Gk3gAAqMjIRMG6/0GsKoOY8zew43MAgDYhFWmdav/NKuvQFQUOgZh59xqkXjQW2gT3JdydHV94n/w6MWsGYi+c4OMXQt4KufcgtUp8H4a2kJkWmJycDJVKhfz8fEV7cXExzGYz0tLSXO6pqKjA1q1bXaJ3URRhsVhYip2IKJTUrLkSVCHzT09ARPUYiE7z3peP7VUENU57WkV0dS0+UXVkj1fPMOWfhGiolI/DO/dt+ECJiMjvQuZfOK1Wi27duuG3336D6FCud9euXVCpVMjIyHC5R61WY8mSJdiwYYOi/Y8//oDZbEb37t0DPm4iIvKOXC2wGa+1aghNvPI3yxqnohWamES0ufIBRZsx11ZaverY7zjx8q2oOrzbbd+W8kL5dcqUedAlt/fHkImIqJFCJrgCgPHjx+PkyZNYtGgR/vzzT6xbtw7Lli3D8OHDkZCQALPZjKNHj6K4uBiAbSphVlYWtm3bhq+++gp///03Nm3ahPfffx99+vRBz549g/wVERGRzF7QopUEV22mzFMca2KTXa6J6HI+9B17yccVf34PU0E28j55EtaKYuR9/n+KzZZFsxElO1fCXJgj9xnVa0iAvgIiImqokFlzBQDdunXD7NmzsWrVKrz11luIjo7G2LFjMWGCbR55aWkpFixYgAkTJmDixIkAgClTpiAuLg4//PADtmzZgqioKAwfPly+h4iIQkNt5iqkfq8XMM7BlLu6TIJKjbbXPQnjmePIeeduAED2ojsV11Qe/AUx/UYDAM6ueg2Vf2+Tz+lSOvp51ERE1BghFVwBQN++fdG3r/u540lJSVi0aJGiTaVSYeTIkRg5cmRTDI+IiHwlr7lqHZkrdWQsoNYAVgsAILKODFNdQZIx9whQE1w5BlYAFPttERFR8PGnMhERNQn7PletZc0VAKROexBRvYeh7U3P1rlRsCAI6PzAZ26DJVP+CQA1QZYTTXSC/wZLRESNFnKZKyIiapns0wKF/2/vzgOjKs/Fj39nXzOTyb6zBAKEsIMCLqhVUEGUXrfaums3rbft77bVa29721t7e7vYutSqrV1sbbUuFHABKhVwAUT2NRBIyL4nk8y+nPP7Y2RgTAJBApmE5/MXc7Z5T3jmnPOc9z3P0Zw7yZV19FSso6f2a1mNzkDuLd+je9c6grX7MRWMw7NzLcG6cpqXP5GwbO4XfkD39jU4Zlx5BlothBDi05LkSgghziGR7nZ0NufgDM07x565+jQsIydhGTkJiCWjnt3vghLFs2ttfBnr2JlYRpRhGVE2OI0UQgjRJznDCSHEOcJXsYXqx++l8v8+R7Cp6qx/vxqvFiinnv7QaHXoLCk9pjtnLx6E1gghxNmz40ALz/5jFy0d/sFuyimTM5wQQpwDVCVK40s/jn1QojS88N8o4eDZbYQSBmLD30T/aC32hM/G7FFYiib2sbQQQgx9kajCz/+6hRXvHuZnf/losJtzymRYoBBCDHNqJEz7ur8mTFP83QRq9mMd3Xt11jPTjljVPHRy6ukv9eNKgwD5d/0MQ2bBILZGCCHOvKde2UFnd+zmn9U89M4XQ6/FQggh+k1VolT+383xz/rUbAzp+fgPbSXS0QicxeTq40RBI8lVv6mhQPzfptzRg9gSIYQ4swLBCN964l2qGroA+PJnJ7PwglGD3KpTJ8MChRBimFJCAer/9HDCNOuYGRjScgDoePclIu4WunevPytDBI8lVzIssL+cs68FYv9vQggxXO0+1MoN//lGPLG6cs7IIZlYgfRcCSHEsNW66jmC9Qfjn00F40m/4g78h7bTtflNol431U9+GYDIxTfjuuiGM9oeNXr0mSs59fSX8/xrMKTnYcoemhcZQghxMpX1bh7+zfvxz+NGuLj32qFbDVXOcEIIMQxFPB14dv4r/nnUf76CRqMBwDp2BpZRU/BX7ojP7975r4TkSgkH0egNaHp5qe2nJcMCT51Go8E2duZgN0MIIQZcOBKlpdPPz/6yBUWNTbvhM2P5wpUT0Go1g9u40yBnOCGEGIY63305/u/C+38TT6yOSrvsC9Q9dyy5ivo9hFpqMGYW4tnzLs3/+BXmERPJ+8IPB65RklwJIURSiSoq+6vaKSlKxaA/c+8/DAQj7K1s593tdby9uZrv3nker75Twb6qdgC0GnjkKxdQVpxxxtpwtsgZTgghhplAfQVdW1cBkD7/bgzOrB7LmHJGk7noPjQGE81LH0UN+qh99us4z1+Me9Py2HaO7EEJ+tGaLKfdJlVV48MCkWeuhBBi0Kmqyi//upV122rRaTWMynNQOiqdnHQbU0syyUqz0tzuozC75/v2jtfS4aexzUtxgROrOfH4vudwG4+9uI2GNm/C9B/94cP4vy0mHd+/Zw4TR6cP3M4NIkmuhBBimOn66K3YP3R6UibN63O5lCmXAdC9fU18iODRxOqoSFcrxszC02+UEo3/U3quhBBicITCUd7aUIXZqGPTnkY2720CYj1YFbVuKmrdPdZJc5j4/Xfno9MdGyb+5geV/OmNvfgCkYRlU1NM/OS+C9EAz/5jF1v2N5+wPdPHZfHvN08jzWE+/Z1LEnKGE0KIYSbYeAiArGu/jtZsO+nymYvuo/qJL/Y6b6CSq+Pf1yTJlRBCnFxUUWl3B8h0DczoAbcnxJ/e2Mvbm6sT5s0uyyEQjLL9YEuv67Z3BfnTm/sozneS7jTz0FPv97ocQGd3kC//ZE2P6bcvLOWCyXlkpVlRFJW9lW1otRpKR6WjG8LPV/VGznBCCDGMKKEA4dY6AMwF4/u1jt6RzuiHX6V97d8I1pWTcdWXaF39HP5D2wi310PxNEJtdUS72zFmj/w4YdPgr9qJOXdMvxK4+JBAQKOXYYFCCNGXcCTKb5ft5l8f1RAMRbnn2jKuvbgYiCVJR0WjCtsPttDaGWD8SBdF2SkJz9d+sLOeZesPcbjOTSAU7fE9AHMn5/LgbbPi6wXDUfyBCD94biPVDV2EIgoAS9dW9Fg3L8PGgtkjmTAyDUVV2VbezEtvH4jP1+u0fO3GKcwqzSHFaoxP12k1TBmbeRp/oeQmyZUQQgwj4bY6UBV0tlT0Ka5TWjftks/F/63Rx06Ebat/T6SzGfeHrycsax07E9/BjwCwlV5A5qL70BpMfW77WM+VBgawAqEQQgx1Xd4QwVCUti4/vkCE6sYu3vqgKj7/d8t2c6i2k10VrbS6Yy8Wf/jO81i/rY53t9clbOuS6QXc8JmxPPnyjnixiE+6as5IPnvpGHLSe94YMxl0mAw6fvn12JDy+lYPX390Lf5gYnJ2yYwCHrhxGgb9seP5hJFpuL0hVm6Itf0bn5vGxdMKTvnvMdRJciWEEMNI1Bd7AaPOfmqJ1SfprI74vz+ZWAHxxArAu/d91EiI7Ou/06Mq4VFq5Ng7rvpaRgghzhUef5jGVi8Om5G7H/lnn8sVZNmpbfbwzpbahOmPHFcQ4nhrt9aydmvishlOM4qqcvfiMiaMTCcj1dzv43Behp3f/ucVvLWhihdW7gfglvnj+NyCniMjtFoN910/hVvmj6PLG2JErqPHMucCSa6EEGIYifq7AdBZ7Ke1HdfFN9G9recJ/5PvxzrKd2AzVb+4jRH3P93rMEHl46RPaz1x1SkhhBiu9hxu49ev7KC2uZvjRvf1KjfDxv/dfyFV9V1879kN8elZLgvNHf745+ICJz+4dw4r3j2cMCQPwGEz8v17ZlNSdHo325x2EzdfMY5RuQ5qmj0suWTMCZd3Ocy4hlGBilMlyZUQQgwToeZqOta9CID2NJMrvd3FqAdfxFseuztqLhiP3hErk1v3x4cI1sVO4unz76Zt9XMAqEEfVb+4jaIHfos+JQ2IJXvBxsN0rH8ptuGTXVEIIcQwEo5EWbb+MO/tqONQL5X4jlowewSfmVmE1aKntsnD9PFZWEx6XOPMPHj7LJ55bSdfu3Eqs0pz2HPgCOt2dWI16fn8leMx6HV84aoJLLxgFM/+YxcVtZ1MHJ3O12+ePqD7cn5ZLucP6BaHJ0muhBBiGIj6uqj740Oo4dh4fK3l9HuINDoD9tILekxPu+wLdKx/CevoqThmXoUxo4CGv/4gPr/ro7fQWuxEu9sJNR/BX7XrWDs9HafdLiGEGAyKonKksYvC7BT0upM/O/qnN/byyr8O9jrPZjFQkGWn/EgH1182ltsXlsbnjchJHE53weQ8LpicF/+c7jDx1X+b0mObLoeZ79w2q7+7I84QSa6EEGIYCNSWxxMrjd6IvfTCM/ZdlqKJWL7ww2OfR02m8L7fUPPrrwDQ+cFrfa7rnHPdGWuXEEKcKeFIlB/9/kO2ljczMtfB+RNzqG7qZlJxBvuq2tHrNFwyo5DxI1woKhj0WpatPxRff8LINGaVZnPdvDG0dPpId1owGXSDuEfiTJHkSgghhriW139N945/AWAZPYWcmx5Goz27J21DahaOmVfT9dGbvc7PuPKL6F05WIpKe50vhBDJwusP8/MXtvDRvqZe51c1dFHVEHuOdMOuhvj0o0UntFoNihIbAm0z6/n9f83Haj72Coq8jNMbti2Sm9TDFUKIIcxXsTWeWAGkf+b2s55YHWUdc2x8f8GXHksobJEyfT7W0VPkHVdCiKQWCkf5wvff6jOxSk3p/ZUTOenW+L+PJlYA184bk5BYieFPeq6EEGIIO/55poIv/hJjZtGgtcUyajLO2ddiyi3GmFGAc/Z1dKx9AdfFN0n5dSGGmboWDxaTHrvFgPHj4W0Hqjt4YeV+Lpqax0XTCljx7mEynGYumVF4wm3VNHWzs6KV2WU5pNpNBEJRbJbBSUheW1tBJNp74Z00h5knv3UpAJv3NlJS5GL1pmqmlmQyrSST3y7bTSgcZdq4LD7c08iInBSunXfiynpi+NGoqpRuSnaNjY3k5OQMdjPEOU7iMDk1vPgj/Ie2kXHVl3BMnz/YzUmgqipEIwPWWyUxKAbbuR6DiqLi9gR54uXtbN57rGfn/humsGrjEQ7WdPa6XmG2HVeKmeYOHzPHZ3PJjAIyUi3sr+rgtbUHOVB9bD2TUUcwFHth7cILRnHrVRM+VaJV09TNtvJm3tlayzUXjuKymX3feHJ7gjzx9+1s3teU0Ov0yFfmUlLowmxKrr6Icz0Ok50kV0OA/IhEMjjX41BVVTrW/Q1Deh4pky4Z7OYQbKrCs+dd3Bv+AUDOzd/FWjxtcBt1hp3rMSgG37kag9sPNLNy4xG27m/CH4ye1e+2mfU8/eDlfQ7H+6TyI+386A8f0tkd7DHvZ1+7CIfdyP/+cTNHGru459oyDDoty9Yfpq7Fk7Dsr791KUU5yfkS3HM1DoeK5ErFhRAiSQWqdtH5/qsAg55cBWr2U//8wwnT9Cnpg9QaIcRwFYkqPPH37fzro5oe82wWA5fPKkqoiPfwnecxeUwG+490sK+ynYxUCxNGulizuQa3N8iazT23A/DDL84hqqj88fU9uFLMTBiVxt9WlwPgDUS49b9XMrsshy9/djLpTkuv2+j2hfjGL9fR1O7rc3++9cS7CZ9/+4/dCZ81Grh7cRnjilxJm1iJ5CfJlRBC9EOorS7+byXoR2vq/QR/NnTvWtdjmu7jl/YKIcTpikQV3ttRzxN/304onNhT9b27z6fNHWDmhGwyUi0suaSYv60up3RUOrPLcgGYPi6L6eOy4uvcec1EgPhLbXdVtNLQ5sXjCzFlbCbFBakAzJyQHV/n5ivGsfzdwzy3PJYAbdzdSCSq8r27z48/w6koKu9sqWFbeQvrttUmtPN/v3oBOek2dDoND/xiba89Wcf79hdmctG0/FP9UwnRgwwLHAKk+1ckg+ESh6qq9qu4gqqqRLvb0KWko9FoqHr0dhR/bNhIzi3fwzqq5wscz7RIdwc1T38NNeQHIOuz/49wWz2oCq6Lbjzr7TnbhksMiqEr2WMwFI7iC0QIRaLsPdyGCrR2+mlq9/HZS8eQmWrhUJ2bsYUuOrsDvLejno6uANnpNnZXtOIJhDEbddQ2e6hu7I5v997ryrhoSj4pNmO/Xp47UKKKyr0//ictHf74tBSrkc8vGMeG3Q3sONjaY52r547k3usm9WhnMBzl8Re3Udvs4Vu3zkBRVD7a18S86QUAffaIJaNkj8NznfRcCSEGXdTrxrt/A5bi6YCK3pmJRjPwJ/BQSzW1z34DOHFlPf+R3bSu/C3h1lrMRROxl10UT6wAuj56a1CSq873X4knVgCmnNHYJ8w96+0QQgyuQCjC5r1N/HPTEY40dpOdZmVWaTavv1dJe1eg13VWbTxyyt8zc0I2ty8sZUROyqBU/NRpNfzy6/OIRBXe2lDFS/88QLcvxNNLdyUsNzrfydjCVK6aMzLeC/ZJJoOOb906M2GaDP0TZ4IkV0Kcowa6ktun5Tu8g8a//TBhmtZsI2Xq5aRe8G/ojntX0ulQVTWeWAHUPvsN7JMvI+OKOxLex6QEvDS++AhqJARAoHoPgeo9iW0+uIVwZxOG1GwGmvfAZpSQn5SyixOmK0E/XVtWxj+nX3EnBpfcuRTiXOHxh6lv8VDX4uF3y3bT5Q3F57V3BdhX1X7K2zQadD2G/Y0pcFKYncIFk/M4/+NhfoPJaY8VsvjClRNItZt45hOJ1b/fNI3Lzxu8V1AI8UmSXAlxDoh0d+At34TekY51zHTUaISGv/6AYG05pryxWEvOwznrKrTGszcsonPDP1BCfoJ1B3rMUwJe3BuX4d23gfy7f4rOknJa36UEfbSv/VuP6Z6d/8JXvpH8e3+BwRl7PsBbsSWeWH2S47xFBGvLCdYfpOap+ym67yn0zszTatvx1GiYppd/AoApdwzBunJAg3XsDBr+eiwBLfjyExjT8wbse4UQyckXCLO/qoMX/1nOwZpOIlElYf7E0bHnnEwGLRt3N+INhLnivBFcOCUvoXx5VFHZX9VOS4ePlk4/b22owqjX8dOvXYTDZqSuxUOWy4pBf/aG/H0aiy4czQWT89i8r4mpYzPJSrOefCUhzjJJroQYRjo3rcC9aTlRT2dsyJtGQ7i9ATV8bJiIIbOIcEt1/HOw/iDB+oN0rH2BlGnzsYwsQ5+ajTnvzL34UAn6aP/XnxOmGdLysE+ah3XsTDrW/hVfxRYi7ma6t68hdc51/dtuJETE3YpGqyVYX4F1zHS0Jivta/9K10dvxZfLv/vndG5Yinfv+yhBHzVPfpW82x/BXDAO/+HtAKTO/Syh5iNE/d0Y0vLQ6I2kXXwz7etfJFh/EFSFhr/9DwVfeoxodztaawpavfG0/i7B+mNVt/yHt9O2+rlel5PESojk0djmxaDX8tdV5eysaGF2WS53XTPxUw2jC0eidHlDvPpOBRt2NdDa6U+Yb7MYCIejzJtewG1XlyaUJ79q7qg+t6vTapg4Oh2IVRW94TMlCfPzM+2n3NbB4nKYmX/+iMFuhhB9koIWQ4A8uCj6w1u+iaZXfnpK69jGz8GYVUTXllVEvZ0J87QWO/ayeVhHTcEyZhpNTc2nHYeqquKv2IoS9NG87FcJ3zXigd8lDFHs3PCPeAJmHXc+jqmfQe/KxeDKpu3tP+Gv3EHeF36IzuYEIFBfQf0fvtPjO+1lF+PZvT62nTEzyFryjXgPXfeOf9Hy+q/jy5pHTCRwJDYEMPv6b2Mbd36P7fmr99Lw5//qMV1rsWMdOxPH9AWY80t6zAdQQgHaVv+ecGcTqCpRTwf2SfNwTJ9P61vP4N2/8YR/PwDHrIVkzL/rpMsNR3IsFGfCgeoO1m2rpaaxG6NBx6UzCplZms2GXQ0UZaeQk27l+Tf3sftQK/5gmEtmFJGbbkWv1/HPTUfYWdGzqMJP778IjRYyUy1YzQY0GjAbE+9nuz1BQmGFN94/zKY9jfgCEdyeIFEl8bJMr9Picpi4YHIedy6aiFZ79p99EslFjoXJTZKrIUB+RKI/jq9mlzJtPuHWGgI1+wAouPdR9K4cgvUHaX3zacLtDWgtdnI//wNM2SOJ+j00/OV7hJp7f+BZZ09DM2oGhYvuRaPV9as9vVXl+2QyA7ES4lnXfQNLUWnC9HB7PbXPfhM1Gk6YrjFaEos6FIwj1HQkoXeuLyO++Sd0lmN3aFVVxVe+ieblT/RYv/C+p3p9pkpVVaofu6dHMno8Q0YBrgtvwFw4npbXn8JfuQNjVhGh5uo+1zkRfWo26VfciRoOYh0746wO30wmciwUp8vjD9PY5mV0XuymzGMvbev1HU6fRorVSDAUIRRReszT6zSMzneiqGDUa+n2halr7kbp4wosI9XCnEm5XDVnJAVZ9kEpJiGSlxwLk5skV0OA/IjEiSjhIC0rnsC7bwMAubf+EEvRRFQlinf/RsxFE9HbU/u3raAPjdFC5wdLcW9chhLwgEYL6rGLBY3BjBoOYsobg3XsTCLuFrRmG66Lb0KjNxDtbqdryyo6Ny7HmFWEfcIcHDOuRGuy0vTqzxJ6Z1IvupG0i2/qsz2h1lp8FVsJHNmNr2JLv/Yha8k3sYwow1u+Cc+edwk2HI4nTqMffrXXdaK+Lrp3voNnz3uEmqpwzl5M+mW39vkd0YCXI7+4DQDL6Ck4Zy0i0tVK9/a3CTYc6nO9k3HN+xzOWQsJtzfgO7QVJeAlde5n0VlP75mz4UKOheLTaGr3sXrTEepbPGwrb8YbiPRYZkROCuGIQn2rt9dtZKRa+MysQrq7PRyq91Ne3QHAtJJMFl04Gq1Ww5Sxmbz2zkH+snL/KbXPaNBx61XjKSvOwGTQ4bAZcdiMklCJPsmxMLlJcjUEyI9I9EUJ+Wl54zd4974PgN6ZSdH9Tw/sdwS8dLz3Mu4tq6CPQg9HafTGPotB2CddgmfvexCNYBk9Fdv42aRMuazfPWGh1lrUcJBgwyF8FVvxV+6If5cpdwy2iRdiTM/HOmZ6YvvDQVrffBpz0UQc0y4/6feoqtKvMvDBxkqiPjfW0VOPrRsNE6gtp3vHO3h2rQVAa0nBMnoKGo2WcHsDlpGTcF1yCxqNBlVVCTVVgqpicOUkVC0UPcmx8NwQVVRqmrp5+8Nq6lo8+AJhWjv9jC10Mf/8EUwfn0Vzh4/mdh9mk54xvZTejkYVvvvMB+yvaicS7fsyR6fVcP8NU+PV5lRVpbM7SF2Lh9wMG4fr3FjNBiaMTEOr1cRjsMsbIqoouFLMCdsLhqO8/u5h0p1mLpqaT0OblxSrEa8/zN7Kdl595yCpKSaMBh33LC7DbjVg0GmxW0/veU1xbpFjYXKT5GoIkB+RiPo9+Ct3oDXbMBeMQ2u0oISD1Dx1P1HPsfK7OTf9J9YxM85IG+or9qL58GU0BhN6R8axAhE6PUR73gm2jp2F1mSJP+90vLw7/rfP55JORTTgRQ36BrRi30CJBrxEu1o/LoYxuOXujxeJKvgCERy2oXcxJ8fCoccXCFPd2I3DZiTv46IJB6o7qG/xMH18Ng6bEUVRiUQVvP4wKzdU8draCgKh6Em23JPJqOOCyXmoqsrmvU14/MeGFNssBuafP4IxBU6yXFYa27y0dwWYOzmPnPT+39SQGBTJQOIwuUm1QCGSXNf2t2l94zc9pmsMJtRwEADnnOtOOIxtIGjtaeTc8v34Z9eFN6DRG0Gjof7P3yPa3UbmtQ+gT0nHd2gbjunz0RpMuC6+KTbkbvd6Ip3NGDKLMGYNTKUnndkGSdrbozPbBuwdXaerszvIu9vrWL3pCFUNXQCcPzGH2xeWotVqsFsM8XfJQKznYFdFC0U5DtIc5r42m1Q8/jB2S/IksecaVVXZWdFKbbOHpnYfNU3dbNnfxPG3b+0WQ0LCAzB5TAaH69w9pgOMznOyYM4IvP4wf3/7wEkTrmAomvD8lNmoY9q4LG69agI56VYM+mO95ONHpn3KPRVCiBOTnqsh4JN3KBrbvCiqSnaaDZ1UDepVIBTBqNfR1O6jtdNPaoqJjFQLiqImvPsjmSlBP/XP/+dJiyCkX3EnzvMWxT93dAU4XO/mSEM3eyvbOFjTSYrVwJjCVKxmA0a9ltwMG/OmF/SoXnVUIBTBH4yQajfFx/0fH4eKoiZUrIpEoni8AQ7WdeNymBmd5yQYjmI26uLrq0oUNRJGYzDJswSnwesPYzHp43//UDjKuq21bN7XxP6qdjz+MIVZKWh1Glo7/Oj1WtyeIOFeHrL/pLLidIwGHVv3N8enzZ2cy7dvnYXHF4oVAsh3YtDrYhfTB1txppgozE45K8ei42OwvsWDCqzZXM3mvU1UNXRhNupIsRkxG3VcPK2AuZNycdhM6HUavIEIUUWhtdOPUa+j2xeipMiFzWJAVUGjiVVlG+6a2n08/dpOHDYjTe0+IPZ7T7EYcdiNzJtewHml/b8j7vWHWbu1lmXrD9HQx/NKp+rmK8ZxyYwC8jJs8WNFVFHxB8I89tI2Nu5u5O7FZVx+XhFL11bQ5vYzqTiDqoYuDtW6MRq0zJmUx2dmFQ74/6n0GIhkIHGY3CS5SnJVu3bS9OYzVEWzaI2mEMKANdiKRzHTpMtG48gipeswFk0YfVoe3Smj6HB7GV+cxaTiDBRFpdMTjN+Z1mhiF8bpTgs1Td3sOdzGzopWHDYj40a4mF2Wi6Ko6HVaigucJ7wIjirqoCd34UiU+lYv0ahKty/E3sp2DlR3sP1Ac6/j7DUaGJnrYMrYTEblOXClmIlEFTJSLeh1WnRaDbnHndDPhpqmbjbubsCg12E26pg+PgujXoe+YTfNL/84vpz74v9Hpc/G1I9iL5P1W3NomfR5WjQZVNR24vaEaGrz0uo+edW8ozJSLdgtBowGLQ6bCa1GQ3VTF41tsYuuFKsBl8OM3WKg2xsgEI79TVs6YtX6XCkm3N4QyidKXmk0oKpgNeuZOT6bJZeMYXS+84yVEO5PLKqqSrcvTJc3SE66jVA4ikajwWI6ex34qqqyt7IdfzA2jFKr0WA26RiV56SippPGNi/NHX6MBi0TRqbR7QvhsMV6lP6ych+7D7UBYDHpMRliCYKiqvTnKO5KMTEq38mUMRlMHpPJb5ftYm9l+8lX7EXpqDSMBh3bD7TEp82bVsCcSblcMKXvd3ApisquilaKC1OxWwyEI1H8wSjrt9VyuM4NxCquTR6bwdSxmSiqyqqNR4gqKjazns17ajlQ68XrD8f/hgNFo4m9kHXhBaNId1iwWvS4UsxDcvjk8baVN/Ozv3xEty/M6HwnNU3dJ020p5Zkcv7EHKxmA+u31XKguoPSUelMLcnk5TUHCEcUMlOttLr9eP3heOlwg17L5DEZhCMKGg2cV5pDTrqNWaXZ1Ld6qWroQqfVkOWyEokqvPTPA6SmmJhaksmYglQUVSUnPblvGspFrUgGEofJTZKrJLfu149Q2Ln1lNYJqAZ+1XUlIVVPh2JDg0oULRpUbJogIVVPms6LU+NjrKGRXF0nrUoK7VEbBk2UxqiTNiWFhqiLyWMyeOCmadgsBo40dDE634nRoONPb+xl6doKAC6amk84EiU7zcYV5xWR/vEFu9sTpKK2E48vTJs7QHOHj7pmD4qqkp9pZ9wIFyVFLgqy7LyzpZbdh1rR67QUZNuZOCqd5g4/bk8QfzCCXqdldL6Tju4AH+xsoLLejccXptMTPOnfw2k3EgxF+z2GP81hprjAyS0LxpOXYUNRY71B2Wmxt9e3dwV4f0d9/KLB6w9T3+plRK4DkyF2Rz+qqLy/o56O7gCH6tzxhFYD1LV4sAcaUdyNvNuRy1TdIa62bMenGtkQHMvOUBFF+la+mPIOAI1RJz9xX4NK7A6sU+NljKGJraFRqPS8CNFqju5DKpGowogcB7aP/z90Oi0eX4jNe5v69bcbSFaznlkTcjDotUwpyaSlw0e3L8ys0mx2H2ojqiikO8zxO82+j3vOKuvdeAMRbGY9UUWlMDuFju4A28pb6OwOYDLqqap3YzToCIWjKGpsOJHdaqC2uZsubxitNlY84uhFpc1iIBiKoqpq/O8zYVQaGiDTZeVAdQdtbj9Gg45Uu4kUm5F0pxkN4A9GmTAyjRG5KRj0Oqoa3Lg9IdKdZto+TmwNOm08gfAHI2zZ38SazTVUNXT1eCnoQDAadMwqzeaymYXkZdg4WNOJ2xPEYTOhKMd+b59MbhvbvFhMelo6/fzlrX1s2d+Myahj4dxRFOWksGlPIxt2NZxSWyaPyWBsYSp7K9vRajWUjU5HUVUKslLYtKeBD3Y2kGI14vGH+pUU9kdRTgqfmVnE2MJU2rsCrNxYFU9Ee+OwGenynrg4y/GumjuSRReMIj/TTlOHj9z0vm/AqKpKbbOH1BQTKYNQpGB/VTu1zd0A7D7cxprNfZcZN+i1TCrOwBsIU9PUja+XKnr9kZ9p4zOzirhyzshB2eezSS5qRTKQOExuklwluZb6ehr+/hMsetCY7ahKFKvTherrJNh4GI0SRdWb0URO3FsRwISOKAb6f/KMqFraFRsfBEvoVswEVAPl4TzC6CnUtTLTVMnawAQ6lMF9s7tRr0Wn02Ix6SkrTqekyBVLxLoCTB6TSWqKiWhUoaHNSyAYZV9VOx/sqmdfZTsGvZZ0p5nGNh8GvZaoop7wrq5Rr+31HSYQe5jalWKiud2H026io7vv5OWxtOcB2BocyXRT1Qn3b6PpQjbrpqESu6uv1Who7vDh9YdJd5rJz0whO91KlstCfqad4oLUk/bGRBWV5nYfzR0+gqEoUUWlyxuiyxskzWEmy2Vl3AgXtc0eurxBmtr9eD1dZGelk/rxszkf7mlEp9Nw0dR87JbYBVVGqpn2rgBt7gB5mXb2VraxeuMRNu1pPGF7hiOtBlwOM25PsM9qZTaLAa0Gun2xBHB0ngOn3YTHH6ayvotQOHZDQKOB6eOyWHxRMcUFTjq6g0SjCsFwFJNBR36Wvc8hnqciGI6iKGpC/Bxp6OI3r+1kVJ6D6y8bywc7G/AFw9Q2exiV62Te9Hz++PpeNuxuIPgpihAcddHUfFJTTDS1+dh+oDnhd5ZiNeIPhkm1G7nzmjIKslLIcllo6fRTkJWCQd9z6JeqqvGXsoajChajnozU2PvBtFoNiqLiC4Q5VOdGq9GQ6bKw/N3DrNxQ1a8hlOdPzMFk1LH7UCsTRqZz/WVjcTlMPPbiNrZ93KN30dR8dLrYM217Dreh02ooK84gN8NGXbOH6qZu5k7KxWTUYbcaSXOYcaWYSLWb0H2K4Wwf7mnkf36/6YTLjBvh4qHbZ5HutPT6Lrrqxi4+2NXAh3saCYSiFBc4cViN7D/STrc3jE6nobbZw6UzChg/Mo10h5kZE7LPiSGVIBe1IjlIHCY3Sa6GgL5+RGokTKilBmNWEWi1RDqb8exeT8f6l/q3Ya0eQ1oO4dY6IBYGGr0RvSuHcEvvz/lURjIoD+dxmXkPRk3sQqrTnEfUks6mJhP/9IxHIfEka9BrGTfCxeg8J1azAV8gzJHGLrp94fgQFb1Ow4VT89FpNdQ0dVNR00maw0xRjoM2tz+e9Dg+7kG4eGoBBdl27BYjaY7ECxHfwS24P1yBIbMQJRhAjQQxZo0g6nVjLpyAOX8sOrsLjVaHEvQTbq9HY0tDZ3MS+bjH6cXV5TS09f78gBaFi0372RfOo0lJBWIPTh/fM2bX+JljOki6OcIEUwup4SbqU6cR0hhJMSqkN21O2KbemYlj1tV0b11NuL0BjdGC1pWHbfJlpM+8ot/lys+k0zmYhyNRVm44wt7KtvjwoFS7CX8wEh/eVToqDafdRDiiEIkqeHwhWt0BRuY6GDfCxYEjHbi9ISJRBafNxJSSDDJTrSiKQmF2ChqNhroWT6z3EPAHIuRn2nE5TNS3eslwmslItWAy6Nh9uI1wRMFpN9LZHWRnRStV9V1kpFpo6fSRk26jON9JfauXLm+IpnYf/mAEg05LeXVHQpJt1GtxOcx4fCGcH++TSqyIxFFZaVYmF2cwuyyHyWMzsZj0RKPKsefZ2r2kOcy9JkiRqIJWozljQyoH0rbyZn70+01EFJXrLi6m2xfivR31ZLoseHwh2ruCXDw1n5F5DtZvq2PJJWPIy7SR7rCQ6Tr2YmS3J8g/P6wmHI4yaUwGZR8PcW5qaiQ3N/eM7kMkqqDTaohEVaobuzhc5+bNDyqpqHWf0e/9pBSrAbvFyILZI7hq7kis5t6fFVU+PmYZDVqeW7GHhlZvQs+c1azn7sVlzD9/YIrInOvkolYkA4nD5CbJ1RBwqj+iqNdNxNOBwZVN1OtGa7IS7mgEVcWYUYAKaHR6tIZj1cFUJZpwAR/pasNXsYXWt545pbZqUjIwTLuGD735pFs1zC7LRRMNEm6rR2u2odHp6dr+NjqrE1QFXc5Ymk1FpGo8mDqr0JntWEZPRTXFxt2fyrNPUa+bxpd+TLCh4uTtNFpAiaJGI8dekKvVo9HpsJddTMaV99LQ7ken1aIoKk67kQ921mOPtFNQ8Rqhmr2x7zQ7Yxe+0SBqyI9iSkGTmoum6UC/223MHkXWkm9gTM+PDSn0dKKzO/v1rqWzaSAP5v5gJF7sore758lOUVQO17vx+EKUFWf0uGsfVVSq6t20dwXISLUwMtcx5Pbx0+roDmAy6HpNBsIRpddepv4azAuKqoYuXn/vMHkZdqqbughHFPYf6WB8kQuADbsbCEcUMpxmvnHLdA7XuQmGongDESrr3ZQf6SDNYSLdGUsis1xWGtq8VH087PVkxhQ4mTe9gB0HW/loXxMAo/IcVNZ3JSzntBt5+sHLOVDdgcmgY+Lo9AH+S5zb5KJWJAOJw+QmydUQMJg/IlVV8VfuxFxQgv/wDnyHtoGqYEjLxT75Utrf+SuKvxs0GnwHPhygb9VgHTMdXUo6ajhA1N9N1NNJ2qWfx1o8DVWJEulsRmO0oPi78R3ejnffBoJ15fEtaM127JMuhmiUiKediLuVqM+NGg6iBHrrkdJwtPcu9lGLwZWNEgmj0WjRO9IJ1Ow79f0Ydx7m/BJCLdVotHpAJdhQEa8AmHfbI5gLx5/qH2hQyMFcDLZkjkGPL8SRxm6KC5yfaohmR1cAh81IKKJwuM6NNxBmz6E2Nu5uoL6fVfgyXRa+f89sRuQ4Tvn7Rf8kcwyKc4fEYXKT5GoIGAo/IlVVaFv1HP7qPahBP5GuVgA0OgNqNIwuJQ2twUy4vQFQMeWOQWdzEu5oINxWD4DemQUaDZHOpj6/R2dLRY2EUIK+XudrjBacsxbimndzrz0FqqqiRsME6w4QrDuIKb8kltwoChFvBx3rXsKza+1J91dnd2EZOQljZiGG9AIMrhz8R3aj0WqJertQgl5Spl2BMaOg179VqLESY/bIpBju119DIQ7F8HYuxmA4orBuaw17K9upaeqmoztIKBxl8phMXA4TE0amMW6EC1dK7H1kQ2H46FB2LsagSD4Sh8lNkqshYKj9iFRVJdzegM7qQGdJLHahhINo9IaEIW+hlmq0Jht6R2z4SrDhULyHTGMwE+luw7v3A6I+NygfP9ek1cX+rdHGEqT8Ekz5Y7GVzEKjO733WEU8nXj3fUCw8TDGjAJMucUEmyrxHdiMKXcM6ZffflrbH6qGWhyK4UdiUAw2iUGRDCQOk1vSJVfl5eUsXbqUuro6bDYbc+fOZeHCheh0fd/h/zTrDCXyI4qJ+rqJdLdBNIIxeySggkY7pHp/hjKJQzHYJAbFYJMYFMlA4jC5nb23Z/ZDZWUljz/+OFOmTGHRokXU1tayfPly/H4/N91004CtI4YmnTUFnTVlsJshhBBCCCFEr5IquVq+fDm5ubnce++9aDQaysrK0Ov1vPrqqyxYsIDU1NQBWUcIIYQQQgghBlrS1HoOh8McOHCAadOmJRQimDFjBoqisGfPngFZRwghhBBCCCHOhKRJrlpbW4lEImRnZydMd7lcGAwGGhoaBmQdIYQQQgghhDgTkmZYoN/vB8BsNveYZzabCQQCA7JOf0WjUVpaWj71+gMpGAzS2Ng42M0Q5ziJQzHYJAbFYJMYFMlA4vDsy8jIQK/vX9qUNMnVyYoW9vXOolNdp790Ol3SVGKRqjAiGUgcisEmMSgGm8SgSAYSh8ktaYYFWiwWIJaNf1IgEOi1d+rTrCOEEEIIIYQQZ0LSJFeZmZlotVqam5sTpnd0dBAOh8nNzR2QdYQQQgghhBDiTEia5MpgMFBSUsK2bdtQFCU+fcuWLWi1WsaPHz8g6wghhBBCCCHEmZA0yRXAwoULqa6u5plnnmHXrl2sXLmS1157jXnz5pGWlkY4HObw4cN0dHT0ex0hhBBCCCGEOBs06smqQpxlO3bsYMWKFTQ0NJCSksLcuXNZtGgRWq2W1tZWHn74YRYtWsQ111zTr3WGA3lwUSQDiUMx2CQGxWCTGBTJQOIwuSVdciV6kh+RSAYSh2KwSQyKwSYxKJKBxGFyGx5dO0IIIYQQQggxyCS5EkIIIYQQQogBIMmVEEIIIYQQQgwASa6EEEIIIYQQYgBIciWEEEIIIYQQA0CSKyGEEEIIIYQYAFKKfQiIRCLo9frBboY4x0kcisEmMSgGm8SgSAYSh8lNkishhBBCCCGEGAAyLFAIIYQQQgghBoAkV0IIIYQQQggxACS5EkIIIYQQQogBIMmVEEIIIYQQQgwASa6EEEIIIYQQYgBIciWEEEIIIYQQA0CSKyGEEEIIIYQYAJJcCSGEEEIIIcQAkORKCCGEEEIIIQaAJFdCCCGEEEIIMQAkuRJCCCGEEEKIASDJlRBCCCGEEEIMAEmuhBBCCCGEEGIA6Ae7AaJv5eXlLF26lLq6Omw2G3PnzmXhwoXodLrBbpoYBr7xjW/g8/l6TP/pT3+K0+mktbWVl19+mQMHDgAwadIkrr/+ehwOR3xZRVF48803+eCDD+jq6iI/P59rr72W0tLSs7YfYujp6Ojghz/8IV/84heZMGFCfLrH4+GVV15h9+7dhEIhxo0bx4033khmZmbC+uvWrWPNmjW0t7eTmZnJVVddxXnnnZewTE1NDa+88gpVVVUYDAZmzJjBkiVLMJvNZ2UfRfLrKw5feukl/vWvf/VYfsmSJVx55ZVA/499ch4XnxSNRnnnnXd47733aGtrw+FwMGXKFBYvXhw/Pg3k+Vdi8OyT5CpJVVZW8vjjjzNlyhQWLVpEbW0ty5cvx+/3c9NNNw1288QQ19rais/n46abbmLkyJEJ8+x2O36/n0cffRSLxcJtt91GIBBg6dKlPPHEEzz00ENotbFO71deeYX169dz7bXXkpOTw7vvvsuTTz7Jt771LUaNGjUIeyaSXXt7O48//niPxF5RFB577DE8Hg833ngjOp2OFStW8Itf/ILvf//7WCwWANasWcPLL7/M1VdfTXFxMVu2bOG5557DYDAwbdo0IBbfjz76KIWFhdx99920t7ezdOlSOjo6+OpXv3rW91kkn77iEKC2tpbS0lKuueaahOlpaWnxf/fn2CfncdGbf/zjH6xZs4Yrr7ySsWPH0tjYyIoVKzh8+DDf/va3CQaDA3b+lRgcHJJcJanly5eTm5vLvffei0ajoaysDL1ez6uvvsqCBQtITU0d7CaKIay2thaAGTNm4HQ6e8xft24dbreb73znO/H5+fn5PPLII2zdupWZM2fS3t7OO++8w7/9279x+eWXAzBx4kR+/OMf8/rrr/O1r33t7O2QSHqKorBx40ZeeeWVXudv2bKF6upqvvvd71JYWAjAmDFjePjhh1m/fj0LFiwgFArx+uuvc+mll7J48WIgFnMej4dly5bFk6tVq1ah1+u5//77MRqNADidTp5++mkqKysl8T+HnSwOIXZ8nD9/PqNHj+51fn+PfXIeF58UCoVYs2YNV1xxRfwYNmHCBOx2O7/73e84cOAAVVVVA3b+lRgcHPLMVRIKh8McOHCAadOmodFo4tNnzJiBoijs2bNnEFsnhoOamhpSUlJ6TawA9uzZQ3FxccL8oqIisrKy2LVrFwD79+9HURSmT58eX0ar1TJ9+nT27dtHOBw+szshhpS6ujpeeOEFZs+ezZ133tlj/p49e8jIyIgnVhBLiMaMGcPOnTuB2F1Yn8+XEHMQOzY2NDTQ0tIS39akSZPiiRXA5MmTMRgM8fgV56aTxeHRXv3j4/CT+nPsk/O46I3X6+XCCy9kxowZCdNzcnIA6OzsHLDzr8Tg4JGeqyTU2tpKJBIhOzs7YbrL5cJgMNDQ0DBILRPDRU1NDRaLhaeeeory8nJUVWXSpEnceOONOJ1OGhoaelzAAmRlZcXjr6GhAYPBkDBU5ugy0WiUlpYW8vLyzsr+iOSXlpbGj370I1wuF+Xl5T3mNzQ0xC8wjpeVlcWWLVsAaGxsBOhxbMzKyorPdzqdtLW19VhGp9ORkZEhx89z3Mni8Giv/rZt2/jLX/6C2+0mPz+f6667jrKyMqB/xz6NRiPncdGDy+Xilltu6TF9+/btQKyHaqDOvxKDg0d6rpKQ3+8H6PXBa7PZTCAQONtNEsNMbW0tbreb4uJi7r//fq6//noOHDjAz3/+cwKBAH6/v9f4M5lM8fgLBALx52COd3S9o3EsBIDNZsPlcvU5vz8xdzSmPhl3x8fciY6fx29LnJtOFoc1NTVALJZuv/12vvKVr2C323nyySfZvXs30L9jn5zHRX8dOnSIVatWMWnSJAoLCwfs/CsxOHik5yoJqap6wvnHd+8K8WncddddmM1mCgoKABg7dix5eXn87Gc/Y8OGDSeNQYg9u3AiEqfiVAxUzPVnO0L0Zc6cOYwaNSreSwWxZ1n+53/+h2XLllFWVjYgcSjHRwGxSn5PPfUUGRkZ3HHHHcDZOxZKDJ45klwloaN3I4LBYI95gUBASgmL0zZmzJhep1ksFmpra7Farb3e1Tr+bllfy/TVuyDEifQ35o5OMxgMCctALOaOLtvXttLT0we87WL4yMjIICMjI2GaTqdjwoQJrF27Fujfse/oha2cx0VfPvjgA1544QVyc3N54IEHsNvtQP+PhRKDyUuGBSahzMxMtFotzc3NCdM7OjoIh8Pk5uYOUsvEcODxeHjvvffiz68cpSgKkUgEu91OdnZ2vDjA8VpaWuLxl52dTSgUwu1291hGr9f3uEAR4kT6G3NAj2Pj0c85OTmYTCZcLlePbUWjUdra2uT4KU5o+/bt8edfjhcOh+MXv/059sl5XJzI8uXL+dOf/kRJSQn/8R//kfD+qoE6/0oMDh5JrpKQwWCgpKSEbdu2JXT9btmyBa1Wy/jx4wexdWKo0+l0vPDCC6xevTph+s6dOwmHw4wbN47S0lIqKiro6uqKz6+urqa5uTn+gsLS0lI0Gk282ADEErStW7dSUlKS0LMgxMmUlpbS1NREXV1dfJrb7aaioiIec8XFxZhMJrZu3Zqw7pYtW8jOzo4n9KWlpezatYtQKBRf5mh8ywuuxYl8+OGHPP/88wnPjAaDQXbt2sW4ceOA/h375Dwu+rJy5UreeOMN5syZw/3339+jB2mgzr8Sg4NHhgUmqYULF/Loo4/yzDPPcOGFF1JXV8fy5cuZN29ej+owQpwKi8XCFVdcwerVq7HZbJSWllJXV8eKFSuYNGkSpaWlFBUV8c477/DLX/6SRYsWEQ6HWbp0KYWFhfESsmlpacydO5dXX32VUChEfn4+7777Lg0NDb1WQxLiRGbOnMnKlSt5/PHHWbJkCQaDgRUrVmC325k3bx4ARqORBQsWsGLFCnQ6HSUlJWzdupWdO3fyxS9+Mb6tBQsW8OGHH/LYY48xf/58Ojs7ee2115g8eTLFxcWDtYtiCLjqqqvYuXMnTzzxBAsWLCAajbJq1SqCwSDXXnst0P9jn5zHxSc1NTWxbNkycnJyuOiiizhy5EjC/MzMTObNmzdg51+JwcGhUeXp36S1Y8cOVqxYQUNDAykpKcydO5dFixbF384txKelKApr165l/fr1tLa2YrfbOe+881i0aFH83UANDQ38/e9/p6KiAoPBQFlZGddff33C8IVIJMKyZcvYtGkTPp8vXrJ4woQJg7VrYggoLy/n0Ucf5etf/3pCrHR0dPDyyy+zZ88eNBoNJSUl3HDDDWRmZsaXUVWVVatWsX79etxuN1lZWVx99dXMmjUr4TsOHTrEq6++ypEjR7BarUyfPp3PfvazmEyms7afIrn1FYeVlZUsW7aMI0eOoCgKY8eOZcmSJeTn58eX6e+xT87j4nirVq3itdde63P+rbfeyoUXXjig51+JwbNPkishhBBCCCGEGACStgohhBBCCCHEAJDkSgghhBBCCCEGgCRXQgghhBBCCDEAJLkSQgghhBBCiAEgyZUQQgghhBBCDABJroQQQgghhBBiAEhyJYQQQgghhBADQD/YDRBCCCEG0oMPPsjSpUsTphkMBpxOJ5MmTeKOO+5g9uzZg9Q6IYQQw5kkV0IIIYalhx56CJfLBUAwGKSxsZHly5dzxx138F//9V98/vOfH+QWCiGEGG4kuRJCCDEsXX755RQUFCRMu+eee7jrrrt45JFHmDZtGqWlpYPUOiGEEMORPHMlhBDinGG1WvnJT36Cqqo8++yzg90cIYQQw4wkV0IIIc4pI0eOZNq0abz33ntEo1EAPvzwQ7785S8ze/ZsJk6cyNy5c/nmN79JfX09AB6Ph8mTJ/PlL3+5x/bef/99xo0bx4oVKwA4dOgQ9957L3PmzGHy5MksWrSI3/72tyiKcvZ2UgghxKCQYYFCCCHOOSUlJWzZsoXa2lrq6+u5++67mThxIl/96lcxGo1s3bqV5cuXc/DgQVasWIHdbufSSy9lzZo1uN1unE5nfFuvv/46VquVyy+/nM7OTu688070ej133303DoeDdevW8fOf/xyfz8e///u/D+JeCyGEONMkuRJCCHHOOZocdXZ28oc//AGXy8Xzzz+PxWIB4OabbyYSifDGG2/Q1NREdnY21157LStXrmT16tXccMMNAIRCIf75z39yxRVXYLFYWLt2LU1NTTz22GNceeWVANxwww3cc889VFdXD87OCiGEOGskuRJCCHHOiUQiAGg0Gn7zm9/Q1dUVT6wgNgzQZDIB4PP5ALjoootwuVy8+eab8eRq3bp1dHd3c8011wCQk5MDwDPPPIPNZuP888/HaDTy3HPPnbV9E0IIMXgkuRJCCHHO6ezsBMDlcqHT6WhoaODJJ5/k4MGD8aGCqqoCxJ+VMhgMXH311bz44ou0tbWRnp7OihUryMjIYO7cuQBMmzaNu+66iz/84Q/cc889WK1WZs+ezZVXXsnChQvR6+W0K4QQw5kUtBBCCHHO2bdvH06nk4KCAv74xz+yZMkS1q9fT0FBAbfeeit//vOf+dKXvtRjvcWLFxONRlm5ciUej4d169Zx9dVXo9Pp4st85zvfYc2aNTz00ENMnz6d999/n29/+9vcdddd8YRNCCHE8CS30IQQQpxTKisr2bNnD0uWLCEUCvGrX/2KadOm8fzzz2M0GuPLLV++vMe6U6dOZcSIEbz99ttkZGQQCARYvHhxfH57ezvl5eXMnDmTO+64gzvuuAOv18tDDz3EqlWr2LVrF5MnTz4r+ymEEOLsk54rIYQQ54xgMMj3vve9eDW/QCCA3+9nxIgRCYlVfX09q1evBoiXaz9q8eLFbN68mTfeeINRo0YxadKk+Ly3336bO+64g3Xr1sWn2Ww2SkpKABJ6uIQQQgw/0nMlhBBiWHr77bdxuVxArKpfXV0db7zxBjU1Nfz3f/83Y8eOBWLPSa1YsQKHw0FJSQnV1dX8/e9/x+/3A+D1ehO2u3jxYp544glWrVrFAw88kDDv6quv5tlnn+XBBx/klltuobCwkMOHD/PCCy8wY8YMJk6ceBb2XAghxGDRqDIAXAghxDDy4IMPsnTp0oRper2e9PR0pk6dym233cbMmTPj85qamvjJT37Cxo0bCQQC5OTkcNlllzF//nxuvPFGHnjgAe67776E7d18881s27aNt99+m8LCwoR5dXV1PP7442zatInW1lYyMzNZsGAB9913HykpKWdux4UQQgw6Sa6EEEKIU/S5z30OgL/97W+D3BIhhBDJRJ65EkIIIU7B/v372bZtG9dff/1gN0UIIUSSkZ4rIYQQoh9ef/113n77bTZs2IDNZuOtt96Kv2hYCCGEAOm5EkIIIfpFp9Oxfv16srKyePLJJyWxEkII0YP0XAkhhBBCCCHEAJCeKyGEEEIIIYQYAJJcCSGEEEIIIcQAkORKCCGEEEIIIQaAJFdCCCGEEEIIMQAkuRJCCCGEEEKIASDJlRBCCCGEEEIMAEmuhBBCCCGEEGIASHIlhBBCCCGEEANAkishhBBCCCGEGAD/HzAAsef76C99AAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 1000x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "%matplotlib inline \n",
+    "\n",
+    "plt.plot(UBAH_results[\"train\"][\"value\"], label=\"Buy and Hold\")\n",
+    "plt.plot(EIIE_results[\"training\"], label=\"EIIE\")\n",
+    "\n",
+    "plt.xlabel(\"Days\")\n",
+    "plt.ylabel(\"Portfolio Value\")\n",
+    "plt.title(\"Performance in training period\")\n",
+    "plt.legend()\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 146,
+   "metadata": {
+    "id": "dQniascoDIH2"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.plot(UBAH_results[\"2020\"][\"value\"], label=\"Buy and Hold\")\n",
+    "plt.plot(EIIE_results[\"2020\"][\"value\"], label=\"EIIE\")\n",
+    "\n",
+    "plt.xlabel(\"Days\")\n",
+    "plt.ylabel(\"Portfolio Value\")\n",
+    "plt.title(\"Performance in 2020\")\n",
+    "plt.legend()\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 147,
+   "metadata": {
+    "id": "1hJtnW7QDIt2"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.plot(UBAH_results[\"2021\"][\"value\"], label=\"Buy and Hold\")\n",
+    "plt.plot(EIIE_results[\"2021\"][\"value\"], label=\"EIIE\")\n",
+    "\n",
+    "plt.xlabel(\"Days\")\n",
+    "plt.ylabel(\"Portfolio Value\")\n",
+    "plt.title(\"Performance in 2021\")\n",
+    "plt.legend()\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 148,
+   "metadata": {
+    "id": "1hJD79w-DJXo"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.plot(UBAH_results[\"2022\"][\"value\"], label=\"Buy and Hold\")\n",
+    "plt.plot(EIIE_results[\"2022\"][\"value\"], label=\"EIIE\")\n",
+    "\n",
+    "plt.xlabel(\"Days\")\n",
+    "plt.ylabel(\"Portfolio Value\")\n",
+    "plt.title(\"Performance in 2022\")\n",
+    "plt.legend()\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We can see that the agent is clearly overfitting, since it achieves great results in training period but is mediocre in testing periods. This is a common problem in this policy gradient algorithm. To deal with this, you can change the hyperparameters."
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "gpuType": "T4",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "1f84695a1caf4c80b29eb5eea90bb29a": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "1.2.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "317393fb13c0449abfff29a4949553a0": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_1f84695a1caf4c80b29eb5eea90bb29a",
+      "placeholder": "​",
+      "style": "IPY_MODEL_a7a6884bfdb642b9b342f7cda49d7d67",
+      "value": " 10/250 [05:53&lt;2:10:07, 32.53s/it]"
+     }
+    },
+    "4b2aa7128c5d4d15bb794eb76faccd6a": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "ProgressView",
+      "bar_style": "danger",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_6a1187acb99d44c68e27cd5aad879ff1",
+      "max": 250,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_6a5c9dbaddc441d390d4827c170cbe9c",
+      "value": 10
+     }
+    },
+    "6a1187acb99d44c68e27cd5aad879ff1": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "1.2.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "6a5c9dbaddc441d390d4827c170cbe9c": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": ""
+     }
+    },
+    "750b2ea28d2a439db3fc5034927dbce2": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_c172e120fc5e4f9ab13bf8599d868b5f",
+       "IPY_MODEL_4b2aa7128c5d4d15bb794eb76faccd6a",
+       "IPY_MODEL_317393fb13c0449abfff29a4949553a0"
+      ],
+      "layout": "IPY_MODEL_8cb75a82e5374c51b1f47a6e15783177"
+     }
+    },
+    "8cb75a82e5374c51b1f47a6e15783177": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "1.2.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "9cb3d937be5d4f7cac192b392218ef37": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "1.2.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "1.2.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "overflow_x": null,
+      "overflow_y": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "a7a6884bfdb642b9b342f7cda49d7d67": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "b27b9cc333ac44a5bb2cec60d02f16c0": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "DescriptionStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "DescriptionStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "1.2.0",
+      "_view_name": "StyleView",
+      "description_width": ""
+     }
+    },
+    "c172e120fc5e4f9ab13bf8599d868b5f": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "1.5.0",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "1.5.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "1.5.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_tooltip": null,
+      "layout": "IPY_MODEL_9cb3d937be5d4f7cac192b392218ef37",
+      "placeholder": "​",
+      "style": "IPY_MODEL_b27b9cc333ac44a5bb2cec60d02f16c0",
+      "value": "  4%"
+     }
+    }
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}
diff --git a/finrl/agents/portfolio_optimization/README.md b/finrl/agents/portfolio_optimization/README.md
new file mode 100644
index 000000000..720f9e187
--- /dev/null
+++ b/finrl/agents/portfolio_optimization/README.md
@@ -0,0 +1,87 @@
+# Portfolio Optimization Agents
+
+This directory contains architectures and algorithms commonly used in portfolio optimization agents.
+
+To instantiate the model, it's necessary to have an instance of [PortfolioOptimizationEnv](/finrl/meta/env_portfolio_optimization/). In the example below, we use the `DRLAgent` class to instantiate a policy gradient ("pg") model. With the dictionary `model_kwargs`, we can set the `PolicyGradient` class parameters and, whith the dictionary `policy_kwargs`, it's possible to change the parameters of the chosen architecture.
+
+```python
+from finrl.agents.portfolio_optimization.models import DRLAgent
+from finrl.agents.portfolio_optimization.architectures import EIIE
+
+# set PolicyGradient algorithm arguments
+model_kwargs = {
+    "lr": 0.01,
+    "policy": EIIE,
+}
+
+# set EIIE architecture arguments
+policy_kwargs = {
+    "k_size": 4
+}
+
+model = DRLAgent(train_env).get_model("pg", model_kwargs, policy_kwargs)
+```
+
+In the example below, the model is trained in 5 episodes (we define an episode as a complete period of the used environment).
+
+```python
+DRLAgent.train_model(model, episodes=5)
+```
+
+It's important that the architecture and the environment have the same `time_window` defined. By default, both of them use 50 timesteps as `time_window`. For more details about what is a time window, check this [article](https://doi.org/10.5753/bwaif.2023.231144).
+
+### Policy Gradient Algorithm
+
+The class `PolicyGradient` implements the Policy Gradient algorithm used in *Jiang et al* paper. This algorithm is inspired by DDPG (deep deterministic policy gradient), but there are a couple of differences:
+- DDPG is an actor-critic algorithm, so it has an actor and a critic neural network. The algorithm below, however, doesn't have a critic neural network and uses the portfolio value as value function: the policy will be updated to maximize the portfolio value.
+- DDPG usually makes use of a noise parameter in the action during training to create an exploratory behavior. PG algorithm, on the other hand, has a full-exploit approach.
+- DDPG randomly samples experiences from its replay buffer. The implemented policy gradient, however, samples a sequential batch of experiences in time, to make it possible to calculate the variation of the portfolio value in the batch and use it as value function.
+
+The algorithm was implemented as follows:
+1. Initializes policy network and replay buffer;
+2. For each episode, do the following:
+    1. For each period of `batch_size` timesteps, do the following:
+        1. For each timestep, define an action to be performed, simulate the timestep and save the experiences in the replay buffer.
+        2. After `batch_size` timesteps are simulated, sample the replay buffer.
+        4. Calculate the value function: $V = \sum\limits_{t=1}^{batch\_size} ln(\mu_{t}(W_{t} \cdot P_{t}))$, where $W_{t}$ is the action performed at timestep t, $P_{t}$ is the price variation vector at timestep t and $\mu_{t}$ is the transaction remainder factor at timestep t. Check *Jiang et al* paper for more details.
+        5. Perform gradient ascent in the policy network.
+    2. If, in the and of episode, there is sequence of remaining experiences in the replay buffer, perform steps 1 to 5 with the remaining experiences.
+
+### References
+
+If you are using one of them in your research, you can use the following references.
+
+#### EIIE Architecture and Policy Gradient algorithm
+
+[A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem](https://doi.org/10.48550/arXiv.1706.10059)
+```
+@misc{jiang2017deep,
+      title={A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem},
+      author={Zhengyao Jiang and Dixing Xu and Jinjun Liang},
+      year={2017},
+      eprint={1706.10059},
+      archivePrefix={arXiv},
+      primaryClass={q-fin.CP}
+}
+```
+
+#### EI3 Architecture
+
+[A Multi-Scale Temporal Feature Aggregation Convolutional Neural Network for Portfolio Management](https://doi.org/10.1145/3357384.3357961)
+```
+@inproceedings{shi2018multiscale,
+               author = {Shi, Si and Li, Jianjun and Li, Guohui and Pan, Peng},
+               title = {A Multi-Scale Temporal Feature Aggregation Convolutional Neural Network for Portfolio Management},
+               year = {2019},
+               isbn = {9781450369763},
+               publisher = {Association for Computing Machinery},
+               address = {New York, NY, USA},
+               url = {https://doi.org/10.1145/3357384.3357961},
+               doi = {10.1145/3357384.3357961},
+               booktitle = {Proceedings of the 28th ACM International Conference on Information and Knowledge Management},
+               pages = {1613–1622},
+               numpages = {10},
+               keywords = {portfolio management, reinforcement learning, inception network, convolution neural network},
+               location = {Beijing, China},
+               series = {CIKM '19} }
+```
diff --git a/finrl/agents/portfolio_optimization/__init__.py b/finrl/agents/portfolio_optimization/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/finrl/agents/portfolio_optimization/algorithms.py b/finrl/agents/portfolio_optimization/algorithms.py
new file mode 100644
index 000000000..13841ba80
--- /dev/null
+++ b/finrl/agents/portfolio_optimization/algorithms.py
@@ -0,0 +1,251 @@
+from __future__ import annotations
+
+import copy
+
+import numpy as np
+import torch
+from torch.optim import AdamW
+from torch.utils.data import DataLoader
+from tqdm import tqdm
+
+from .architectures import EIIE
+from .utils import PVM
+from .utils import ReplayBuffer
+from .utils import RLDataset
+
+
+class PolicyGradient:
+    """Class implementing policy gradient algorithm to train portfolio
+    optimization agents.
+
+    Note:
+        During testing, the agent is optimized through online learning.
+        The parameters of the policy is updated repeatedly after a constant
+        period of time. To disable it, set learning rate to 0.
+
+    Attributes:
+        train_env: Environment used to train the agent
+        train_policy: Policy used in training.
+        test_env: Environment used to test the agent.
+        test_policy: Policy after test online learning.
+    """
+
+    def __init__(
+        self,
+        env,
+        policy=EIIE,
+        policy_kwargs=None,
+        validation_env=None,
+        batch_size=100,
+        lr=1e-3,
+        optimizer=AdamW,
+        device="cpu",
+    ):
+        """Initializes Policy Gradient for portfolio optimization.
+
+        Args:
+          env: Training Environment.
+          policy: Policy architecture to be used.
+          policy_kwargs: Arguments to be used in the policy network.
+          validation_env: Validation environment.
+          batch_size: Batch size to train neural network.
+          lr: policy Neural network learning rate.
+          optimizer: Optimizer of neural network.
+          device: Device where neural network is run.
+        """
+        self.policy = policy
+        self.policy_kwargs = {} if policy_kwargs is None else policy_kwargs
+        self.validation_env = validation_env
+        self.batch_size = batch_size
+        self.lr = lr
+        self.optimizer = optimizer
+        self.device = device
+        self._setup_train(env, self.policy, self.batch_size, self.lr, self.optimizer)
+
+    def _setup_train(self, env, policy, batch_size, lr, optimizer):
+        """Initializes algorithm before training.
+
+        Args:
+          env: environment.
+          policy: Policy architecture to be used.
+          batch_size: Batch size to train neural network.
+          lr: Policy neural network learning rate.
+          optimizer: Optimizer of neural network.
+        """
+        # environment
+        self.train_env = env
+
+        # neural networks
+        self.train_policy = policy(**self.policy_kwargs).to(self.device)
+        self.train_optimizer = optimizer(self.train_policy.parameters(), lr=lr)
+
+        # replay buffer and portfolio vector memory
+        self.train_batch_size = batch_size
+        self.train_buffer = ReplayBuffer(capacity=batch_size)
+        self.train_pvm = PVM(self.train_env.episode_length, env.portfolio_size)
+
+        # dataset and dataloader
+        dataset = RLDataset(self.train_buffer)
+        self.train_dataloader = DataLoader(
+            dataset=dataset, batch_size=batch_size, shuffle=False, pin_memory=True
+        )
+
+    def train(self, episodes=100):
+        """Training sequence.
+
+        Args:
+            episodes: Number of episodes to simulate.
+        """
+        for i in tqdm(range(1, episodes + 1)):
+            obs = self.train_env.reset()  # observation
+            self.train_pvm.reset()  # reset portfolio vector memory
+            done = False
+
+            while not done:
+                # define last_action and action and update portfolio vector memory
+                last_action = self.train_pvm.retrieve()
+                obs_batch = np.expand_dims(obs, axis=0)
+                last_action_batch = np.expand_dims(last_action, axis=0)
+                action = self.train_policy(obs_batch, last_action_batch)
+                self.train_pvm.add(action)
+
+                # run simulation step
+                next_obs, reward, done, info = self.train_env.step(action)
+
+                # add experience to replay buffer
+                exp = (obs, last_action, info["price_variation"], info["trf_mu"])
+                self.train_buffer.append(exp)
+
+                # update policy networks
+                if len(self.train_buffer) == self.train_batch_size:
+                    self._gradient_ascent()
+
+                obs = next_obs
+
+            # gradient ascent with episode remaining buffer data
+            self._gradient_ascent()
+
+            # validation step
+            if self.validation_env:
+                self.test(self.validation_env)
+
+    def _setup_test(self, env, policy, batch_size, lr, optimizer):
+        """Initializes algorithm before testing.
+
+        Args:
+          env: Environment.
+          policy: Policy architecture to be used.
+          batch_size: batch size to train neural network.
+          lr: policy neural network learning rate.
+          optimizer: Optimizer of neural network.
+        """
+        # environment
+        self.test_env = env
+
+        # process None arguments
+        policy = self.train_policy if policy is None else policy
+        lr = self.lr if lr is None else lr
+        optimizer = self.optimizer if optimizer is None else optimizer
+
+        # neural networks
+        # define policy
+        self.test_policy = copy.deepcopy(policy)
+        self.test_optimizer = optimizer(self.test_policy.parameters(), lr=lr)
+
+        # replay buffer and portfolio vector memory
+        self.test_buffer = ReplayBuffer(capacity=batch_size)
+        self.test_pvm = PVM(self.test_env.episode_length, env.portfolio_size)
+
+        # dataset and dataloader
+        dataset = RLDataset(self.test_buffer)
+        self.test_dataloader = DataLoader(
+            dataset=dataset, batch_size=batch_size, shuffle=False, pin_memory=True
+        )
+
+    def test(
+        self, env, policy=None, online_training_period=10, lr=None, optimizer=None
+    ):
+        """Tests the policy with online learning.
+
+        Args:
+          env: Environment to be used in testing.
+          policy: Policy architecture to be used. If None, it will use the training
+            architecture.
+          online_training_period: Period in which an online training will occur. To
+            disable online learning, use a very big value.
+          batch_size: Batch size to train neural network. If None, it will use the
+            training batch size.
+          lr: Policy neural network learning rate. If None, it will use the training
+            learning rate
+          optimizer: Optimizer of neural network. If None, it will use the training
+            optimizer
+
+        Note:
+            To disable online learning, set learning rate to 0 or a very big online
+            training period.
+        """
+        self._setup_test(env, policy, online_training_period, lr, optimizer)
+
+        obs = self.test_env.reset()  # observation
+        self.test_pvm.reset()  # reset portfolio vector memory
+        done = False
+        steps = 0
+
+        while not done:
+            steps += 1
+            # define last_action and action and update portfolio vector memory
+            last_action = self.test_pvm.retrieve()
+            obs_batch = np.expand_dims(obs, axis=0)
+            last_action_batch = np.expand_dims(last_action, axis=0)
+            action = self.test_policy(obs_batch, last_action_batch)
+            self.test_pvm.add(action)
+
+            # run simulation step
+            next_obs, reward, done, info = self.test_env.step(action)
+
+            # add experience to replay buffer
+            exp = (obs, last_action, info["price_variation"], info["trf_mu"])
+            self.test_buffer.append(exp)
+
+            # update policy networks
+            if steps % online_training_period == 0:
+                self._gradient_ascent(test=True)
+
+            obs = next_obs
+
+    def _gradient_ascent(self, test=False):
+        """Performs the gradient ascent step in the policy gradient algorithm.
+
+        Args:
+            test: If true, it uses the test dataloader and policy.
+        """
+        # get batch data from dataloader
+        obs, last_actions, price_variations, trf_mu = (
+            next(iter(self.test_dataloader))
+            if test
+            else next(iter(self.train_dataloader))
+        )
+        obs = obs.to(self.device)
+        last_actions = last_actions.to(self.device)
+        price_variations = price_variations.to(self.device)
+        trf_mu = trf_mu.unsqueeze(1).to(self.device)
+
+        # define policy loss (negative for gradient ascent)
+        mu = (
+            self.test_policy.mu(obs, last_actions)
+            if test
+            else self.train_policy.mu(obs, last_actions)
+        )
+        policy_loss = -torch.mean(
+            torch.log(torch.sum(mu * price_variations * trf_mu, dim=1))
+        )
+
+        # update policy network
+        if test:
+            self.test_policy.zero_grad()
+            policy_loss.backward()
+            self.test_optimizer.step()
+        else:
+            self.train_policy.zero_grad()
+            policy_loss.backward()
+            self.train_optimizer.step()
diff --git a/finrl/agents/portfolio_optimization/architectures.py b/finrl/agents/portfolio_optimization/architectures.py
new file mode 100644
index 000000000..571badc9c
--- /dev/null
+++ b/finrl/agents/portfolio_optimization/architectures.py
@@ -0,0 +1,261 @@
+from __future__ import annotations
+
+import numpy as np
+import torch
+from torch import nn
+
+
+class EIIE(nn.Module):
+    def __init__(
+        self,
+        initial_features=3,
+        k_size=3,
+        conv_mid_features=2,
+        conv_final_features=20,
+        time_window=50,
+        device="cpu",
+    ):
+        """EIIE (ensemble of identical independent evaluators) policy network
+        initializer.
+
+        Args:
+            initial_features: Number of input features.
+            k_size: Size of first convolutional kernel.
+            conv_mid_features: Size of intermediate convolutional channels.
+            conv_final_features: Size of final convolutional channels.
+            time_window: Size of time window used as agent's state.
+            device: Device in which the neural network will be run.
+
+        Note:
+            Reference article: https://doi.org/10.48550/arXiv.1706.10059.
+        """
+        super().__init__()
+        self.device = device
+
+        n_size = time_window - k_size + 1
+
+        self.sequential = nn.Sequential(
+            nn.Conv2d(
+                in_channels=initial_features,
+                out_channels=conv_mid_features,
+                kernel_size=(1, k_size),
+            ),
+            nn.ReLU(),
+            nn.Conv2d(
+                in_channels=conv_mid_features,
+                out_channels=conv_final_features,
+                kernel_size=(1, n_size),
+            ),
+            nn.ReLU(),
+        )
+
+        self.final_convolution = nn.Conv2d(
+            in_channels=conv_final_features + 1, out_channels=1, kernel_size=(1, 1)
+        )
+
+        self.softmax = nn.Sequential(nn.Softmax(dim=-1))
+
+    def mu(self, observation, last_action):
+        """Defines a most favorable action of this policy given input x.
+
+        Args:
+          observation: environment observation.
+          last_action: Last action performed by agent.
+
+        Returns:
+          Most favorable action.
+        """
+
+        if isinstance(observation, np.ndarray):
+            observation = torch.from_numpy(observation).to(self.device)
+        if isinstance(last_action, np.ndarray):
+            last_action = torch.from_numpy(last_action).to(self.device)
+
+        last_stocks, cash_bias = self._process_last_action(last_action)
+        cash_bias = torch.zeros_like(cash_bias).to(self.device)
+
+        output = self.sequential(observation)  # shape [N, 20, PORTFOLIO_SIZE, 1]
+        output = torch.cat(
+            [last_stocks, output], dim=1
+        )  # shape [N, 21, PORTFOLIO_SIZE, 1]
+        output = self.final_convolution(output)  # shape [N, 1, PORTFOLIO_SIZE, 1]
+        output = torch.cat(
+            [cash_bias, output], dim=2
+        )  # shape [N, 1, PORTFOLIO_SIZE + 1, 1]
+
+        # output shape must be [N, features] = [1, PORTFOLIO_SIZE + 1], being N batch size (1)
+        # and size the number of features (weights vector).
+        output = torch.squeeze(output, 3)
+        output = torch.squeeze(output, 1)  # shape [N, PORTFOLIO_SIZE + 1]
+
+        output = self.softmax(output)
+
+        return output
+
+    def forward(self, observation, last_action):
+        """Policy network's forward propagation.
+
+        Args:
+          observation: Environment observation (dictionary).
+          last_action: Last action performed by the agent.
+
+        Returns:
+          Action to be taken (numpy array).
+        """
+        mu = self.mu(observation, last_action)
+        action = mu.cpu().detach().numpy().squeeze()
+        return action
+
+    def _process_last_action(self, last_action):
+        """Process the last action to retrieve cash bias and last stocks.
+
+        Args:
+          last_action: Last performed action.
+
+        Returns:
+            Last stocks and cash bias.
+        """
+        batch_size = last_action.shape[0]
+        stocks = last_action.shape[1] - 1
+        last_stocks = last_action[:, 1:].reshape((batch_size, 1, stocks, 1))
+        cash_bias = last_action[:, 0].reshape((batch_size, 1, 1, 1))
+        return last_stocks, cash_bias
+
+
+class EI3(nn.Module):
+    def __init__(
+        self,
+        initial_features=3,
+        k_short=3,
+        k_medium=21,
+        conv_mid_features=3,
+        conv_final_features=20,
+        time_window=50,
+        device="cpu",
+    ):
+        """EI3 (ensemble of identical independent inception) policy network
+        initializer.
+
+        Args:
+            initial_features: Number of input features.
+            k_short: Size of short convolutional kernel.
+            k_medium: Size of medium convolutional kernel.
+            conv_mid_features: Size of intermediate convolutional channels.
+            conv_final_features: Size of final convolutional channels.
+            time_window: Size of time window used as agent's state.
+            device: Device in which the neural network will be run.
+
+        Reference:
+            Reference article: https://doi.org/10.1145/3357384.3357961.
+        """
+        super().__init__()
+        self.device = device
+
+        n_short = time_window - k_short + 1
+        n_medium = time_window - k_medium + 1
+        n_long = time_window
+
+        self.short_term = nn.Sequential(
+            nn.Conv2d(
+                in_channels=initial_features,
+                out_channels=conv_mid_features,
+                kernel_size=(1, k_short),
+            ),
+            nn.ReLU(),
+            nn.Conv2d(
+                in_channels=conv_mid_features,
+                out_channels=conv_final_features,
+                kernel_size=(1, n_short),
+            ),
+            nn.ReLU(),
+        )
+
+        self.mid_term = nn.Sequential(
+            nn.Conv2d(
+                in_channels=3, out_channels=conv_mid_features, kernel_size=(1, k_medium)
+            ),
+            nn.ReLU(),
+            nn.Conv2d(
+                in_channels=conv_mid_features,
+                out_channels=conv_final_features,
+                kernel_size=(1, n_medium),
+            ),
+            nn.ReLU(),
+        )
+
+        self.long_term = nn.Sequential(nn.MaxPool2d(kernel_size=(1, n_long)), nn.ReLU())
+
+        self.final_convolution = nn.Conv2d(
+            in_channels=2 * conv_final_features + initial_features + 1,
+            out_channels=1,
+            kernel_size=(1, 1),
+        )
+
+        self.softmax = nn.Sequential(nn.Softmax(dim=-1))
+
+    def mu(self, observation, last_action):
+        """Defines a most favorable action of this policy given input x.
+
+        Args:
+          observation: environment observation.
+          last_action: Last action performed by agent.
+
+        Returns:
+          Most favorable action.
+        """
+
+        if isinstance(observation, np.ndarray):
+            observation = torch.from_numpy(observation).to(self.device)
+        if isinstance(last_action, np.ndarray):
+            last_action = torch.from_numpy(last_action).to(self.device)
+
+        last_stocks, cash_bias = self._process_last_action(last_action)
+        cash_bias = torch.zeros_like(cash_bias).to(self.device)
+
+        short_features = self.short_term(observation.float())
+        medium_features = self.mid_term(observation.float())
+        long_features = self.long_term(observation.float())
+
+        features = torch.cat(
+            [last_stocks, short_features, medium_features, long_features], dim=1
+        )
+        output = self.final_convolution(features)
+        output = torch.cat([cash_bias, output], dim=2)
+
+        # output shape must be [N, features] = [1, PORTFOLIO_SIZE + 1], being N batch size (1)
+        # and size the number of features (weights vector).
+        output = torch.squeeze(output, 3)
+        output = torch.squeeze(output, 1)  # shape [N, PORTFOLIO_SIZE + 1]
+
+        output = self.softmax(output)
+
+        return output
+
+    def forward(self, observation, last_action):
+        """Policy network's forward propagation.
+
+        Args:
+          observation: Environment observation (dictionary).
+          last_action: Last action performed by the agent.
+
+        Returns:
+          Action to be taken (numpy array).
+        """
+        mu = self.mu(observation, last_action)
+        action = mu.cpu().detach().numpy().squeeze()
+        return action
+
+    def _process_last_action(self, last_action):
+        """Process the last action to retrieve cash bias and last stocks.
+
+        Args:
+          last_action: Last performed action.
+
+        Returns:
+            Last stocks and cash bias.
+        """
+        batch_size = last_action.shape[0]
+        stocks = last_action.shape[1] - 1
+        last_stocks = last_action[:, 1:].reshape((batch_size, 1, stocks, 1))
+        cash_bias = last_action[:, 0].reshape((batch_size, 1, 1, 1))
+        return last_stocks, cash_bias
diff --git a/finrl/agents/portfolio_optimization/models.py b/finrl/agents/portfolio_optimization/models.py
new file mode 100644
index 000000000..bfaa537fa
--- /dev/null
+++ b/finrl/agents/portfolio_optimization/models.py
@@ -0,0 +1,57 @@
+"""
+DRL models to solve the portfolio optimization task with reinforcement learning.
+This agent was developed to work with environments like PortfolioOptimizationEnv.
+"""
+from __future__ import annotations
+
+from .algorithms import PolicyGradient
+
+MODELS = {"pg": PolicyGradient}
+
+
+class DRLAgent:
+    """
+    Implementation for DRL algorithms for portfolio optimization.
+
+    Attributes
+    ----------
+        env: gym environment class
+            user-defined class
+    Methods
+    -------
+        get_model()
+            setup DRL algorithms
+        train_model()
+            train DRL algorithms in a train dataset
+            and output the trained model
+        DRL_prediction()
+            make a prediction in a test dataset and get results
+    """
+
+    def __init__(self, env):
+        self.env = env
+
+    def get_model(self, model_name, model_kwargs=None, policy_kwargs=None):
+        if model_name not in MODELS:
+            raise NotImplementedError("The model requested was not implemented.")
+
+        model = MODELS[model_name]
+        model_kwargs = {} if model_kwargs is None else model_kwargs
+        if policy_kwargs is not None:
+            model_kwargs["policy_kwargs"] = policy_kwargs
+        return model(self.env, **model_kwargs)
+
+    @staticmethod
+    def train_model(model, episodes=100):
+        model.train(episodes)
+
+    @staticmethod
+    def DRL_validation(
+        model,
+        test_env,
+        policy=None,
+        online_training_period=10,
+        learning_rate=None,
+        optimizer=None,
+    ):
+        model.test(test_env, policy, online_training_period, learning_rate, optimizer)
diff --git a/finrl/agents/portfolio_optimization/utils.py b/finrl/agents/portfolio_optimization/utils.py
new file mode 100644
index 000000000..695e8b023
--- /dev/null
+++ b/finrl/agents/portfolio_optimization/utils.py
@@ -0,0 +1,94 @@
+from __future__ import annotations
+
+from collections import deque
+
+import numpy as np
+from torch.utils.data.dataset import IterableDataset
+
+
+class PVM:
+    def __init__(self, capacity, portfolio_size):
+        """Initializes portfolio vector memory.
+
+        Args:
+          capacity: Max capacity of memory.
+          portfolio_size: Portfolio size.
+        """
+        # initially, memory will have the same actions
+        self.capacity = capacity
+        self.portfolio_size = portfolio_size
+        self.reset()
+
+    def reset(self):
+        self.memory = [np.array([1] + [0] * self.portfolio_size, dtype=np.float32)] * (
+            self.capacity + 1
+        )
+        self.index = 0  # initial index to retrieve data
+
+    def retrieve(self):
+        last_action = self.memory[self.index]
+        self.index = 0 if self.index == self.capacity else self.index + 1
+        return last_action
+
+    def add(self, action):
+        self.memory[self.index] = action
+
+
+class ReplayBuffer:
+    def __init__(self, capacity):
+        """Initializes replay buffer.
+
+        Args:
+          capacity: Max capacity of buffer.
+        """
+        self.buffer = deque(maxlen=capacity)
+
+    def __len__(self):
+        """Represents the size of the buffer
+
+        Returns:
+          Size of the buffer.
+        """
+        return len(self.buffer)
+
+    def append(self, experience):
+        """Append experience to buffer. When buffer is full, it pops
+           an old experience.
+
+        Args:
+          experience: experience to be saved.
+        """
+        self.buffer.append(experience)
+
+    def sample(self):
+        """Sample from replay buffer. All data from replay buffer is
+        returned and the buffer is cleared.
+
+        Returns:
+          Sample of batch_size size.
+        """
+        buffer = list(self.buffer)
+        self.buffer.clear()
+        return buffer
+
+
+class RLDataset(IterableDataset):
+    def __init__(self, buffer):
+        """Initializes reinforcement learning dataset.
+
+        Args:
+            buffer: replay buffer to become iterable dataset.
+
+        Note:
+            It's a subclass of pytorch's IterableDataset,
+            check https://pytorch.org/docs/stable/data.html#torch.utils.data.IterableDataset
+        """
+        self.buffer = buffer
+
+    def __iter__(self):
+        """Iterates over RLDataset.
+
+        Returns:
+          Every experience of a sample from replay buffer.
+        """
+        yield from self.buffer.sample()
diff --git a/finrl/meta/env_portfolio_optimization/README.md b/finrl/meta/env_portfolio_optimization/README.md
new file mode 100644
index 000000000..6e8bd5c43
--- /dev/null
+++ b/finrl/meta/env_portfolio_optimization/README.md
@@ -0,0 +1,68 @@
+# PortfolioOptimizationEnv (POE)
+
+This environment simulates the effects of the market in a portfolio that is periodically rebalanced through a reinforcement learning agent. At every timestep $t$, the agent is responsible for determining a portfolio vector $W_{t}$ which contains the percentage of money invested in each stock. The environment, then, utilizes data provided by the user to simulate the new portfolio value at time-step $t+1$.
+
+For more details on the formulation of this problem, check the following paper:
+
+[POE: A General Portfolio Optimization Environment for FinRL](https://doi.org/10.5753/bwaif.2023.231144)
+```
+@inproceedings{bwaif,
+ author = {Caio Costa and Anna Costa},
+ title = {POE: A General Portfolio Optimization Environment for FinRL},
+ booktitle = {Anais do II Brazilian Workshop on Artificial Intelligence in Finance},
+ location = {João Pessoa/PB},
+ year = {2023},
+ keywords = {},
+ issn = {0000-0000},
+ pages = {132--143},
+ publisher = {SBC},
+ address = {Porto Alegre, RS, Brasil},
+ doi = {10.5753/bwaif.2023.231144},
+ url = {https://sol.sbc.org.br/index.php/bwaif/article/view/24959}
+}
+```
+
+## Inputs
+This environment simulates the interactions between an agent and the financial market
+based on data provided by a dataframe. The dataframe contains the time series of
+features defined by the user (such as closing, high and low prices) and must have
+a time and a tic column with a list of datetimes and ticker symbols respectively.
+An example of dataframe is shown below:
+``````
+    date        high            low             close           tic
+0   2020-12-23  0.157414        0.127420        0.136394        ADA-USD
+1   2020-12-23  34.381519       30.074295       31.097898       BNB-USD
+2   2020-12-23  24024.490234    22802.646484    23241.345703    BTC-USD
+3   2020-12-23  0.004735        0.003640        0.003768        DOGE-USD
+4   2020-12-23  637.122803      560.364258      583.714600      ETH-USD
+... ...         ...             ...             ...             ...
+``````
+
+## Actions
+
+At each time step, the environment expects an action that is a one-dimensional Box of shape (n+1,), where $n$ is the number of stocks in the portfolio. This action is called *portfolio vector* and contains, for the remaining cash and for each stock, the percentage of allocated money.
+
+For example: given a portfolio of three stocks, a valid portfolio vector would b $W_{t} = [0.25, 0.4, 0.2, 0.15]$. In this example, 25% of the money is not invested (remaining cash), 40% is invested in stock 1, 20% in stock 2 and 15% in sotck 3.
+
+**Note:** It's important that the sum of the values in the portfolio vator is equal (or very close) to 1. If it's not, POE will apply a softmax normalization.
+
+## Observations
+
+POE can return two types of observations during simulation: a Dict or a Box.
+
+- The box is a three-dimensional array of shape $(f, n, t)$, where $f$ s the number of features, $n$ is the number of stocks in the portfolio and $t$ is the time series timw window. This observation basically only contains the current state of the agent.
+
+- The dict representation, on the other hand, is a dictionary containing the state and the last portfolio vector, like below:
+
+```json
+{
+"state": "three-dimensional Box (f, n, t representing the time series",
+"last_action": "one-dimensional Box (n+1,) representing the portfolio weights"
+}
+```
+
+## Rewards
+Given the simulation of timestep $t$, the reward is given by the following formula: $r_{t} = ln(V_{t}/V_{t-1})$, where $V_{t}$ is the value of the portfolio at time $t$. By using this formulation, the reward is negative whenever the portfolio value decreases due to a rebalancing and is positive otherwise.
+
+## Example
+A jupyter notebook using this environment can be found [here](/examples/FinRL_PortfolioOptimizationEnv_Demo.ipynb).
diff --git a/finrl/meta/env_portfolio_optimization/__init__.py b/finrl/meta/env_portfolio_optimization/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/finrl/meta/env_portfolio_optimization/env_portfolio_optimization.py b/finrl/meta/env_portfolio_optimization/env_portfolio_optimization.py
new file mode 100644
index 000000000..533d56ce5
--- /dev/null
+++ b/finrl/meta/env_portfolio_optimization/env_portfolio_optimization.py
@@ -0,0 +1,644 @@
+"""From FinRL https://github.com/AI4Finance-LLC/FinRL/tree/master/finrl/env"""
+from __future__ import annotations
+
+import math
+
+import gym
+import matplotlib
+import numpy as np
+import pandas as pd
+from gym import spaces
+from gym.utils import seeding
+
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+from stable_baselines3.common.vec_env import DummyVecEnv
+from pathlib import Path
+
+try:
+    import quantstats as qs
+except ModuleNotFoundError:
+    raise ModuleNotFoundError(
+        """QuantStats module not found, environment can't plot results and calculate indicadors.
+        This module is not installed with FinRL. Install by running one of the options:
+        pip install quantstats --upgrade --no-cache-dir
+        conda install -c ranaroussi quantstats
+        """
+    )
+
+
+class PortfolioOptimizationEnv(gym.Env):
+    """A portfolio allocation environment for OpenAI gym.
+
+    This environment simulates the interactions between an agent and the financial market
+    based on data provided by a dataframe. The dataframe contains the time series of
+    features defined by the user (such as closing, high and low prices) and must have
+    a time and a tic column with a list of datetimes and ticker symbols respectively.
+    An example of dataframe is shown below::
+
+            date        high            low             close           tic
+        0   2020-12-23  0.157414        0.127420        0.136394        ADA-USD
+        1   2020-12-23  34.381519       30.074295       31.097898       BNB-USD
+        2   2020-12-23  24024.490234    22802.646484    23241.345703    BTC-USD
+        3   2020-12-23  0.004735        0.003640        0.003768        DOGE-USD
+        4   2020-12-23  637.122803      560.364258      583.714600      ETH-USD
+        ... ...         ...             ...             ...             ...
+
+    Based on this dataframe, the environment will create an observation space that can
+    be a Dict or a Box. The Box observation space is a three-dimensional array of shape
+    (f, n, t), where f is the number of features, n is the number of stocks in the
+    portfolio and t is the user-defined time window. If the environment is created with
+    the parameter return_last_action set to True, the observation space is a Dict with
+    the following keys::
+
+        {
+        "state": three-dimensional Box (f, n, t) representing the time series,
+        "last_action": one-dimensional Box (n+1,) representing the portfolio weights
+        }
+
+    Note that the action space of this environment is an one-dimensional Box with size
+    n + 1 because the portfolio weights must contains the weights related to all the
+    stocks in the portfolio and to the remaining cash.
+
+    Attributes:
+        action_space: Action space.
+        observation_space: Observation space.
+        episode_length: Number of timesteps of an episode.
+        portfolio_size: Number of stocks in the portfolio.
+    """
+
+    metadata = {"render.modes": ["human"]}
+
+    def __init__(
+        self,
+        df,
+        initial_amount,
+        order_df=True,
+        return_last_action=False,
+        normalize_df="by_previous_time",
+        reward_scaling=1,
+        comission_fee_model="trf",
+        comission_fee_pct=0,
+        features=["close", "high", "low"],
+        valuation_feature="close",
+        time_column="date",
+        time_format="%Y-%m-%d",
+        tic_column="tic",
+        time_window=1,
+        cwd="./",
+        new_gym_api=False,
+    ):
+        """Initializes environment's instance.
+
+        Args:
+            df: Dataframe with market information over a period of time.
+            initial_amount: Initial amount of cash available to be invested.
+            order_df: If True input dataframe is ordered by time.
+            return_last_action: If True, observations also return the last performed
+                action. Note that, in that case, the observation space is a Dict.
+            normalize_df: Defines the normalization method applied to input dataframe.
+                Possible values are "by_previous_time", "by_fist_time_window_value",
+                "by_COLUMN_NAME" (where COLUMN_NAME must be changed to a real column
+                name) and a custom function. If None no normalization is done.
+            reward_scaling: A scaling factor to multiply the reward function. This
+                factor can help training.
+            comission_fee_model: Model used to simulate comission fee. Possible values
+                are "trf" (for transaction remainder factor model) and "wvm" (for weights
+                vector modifier model). If None, commission fees are not considered.
+            comission_fee_pct: Percentage to be used in comission fee. It must be a value
+                between 0 and 1.
+            features: List of features to be considered in the observation space. The
+                items of the list must be names of columns of the input dataframe.
+            valuation_feature: Feature to be considered in the portfolio value calculation.
+            time_column: Name of the dataframe's column that contain the datetimes that
+                index the dataframe.
+            time_format: Formatting string of time column.
+            tic_name: Name of the dataframe's column that contain ticker symbols.
+            time_window: Size of time window.
+            cwd: Local repository in which resulting graphs will be saved.
+            new_gym_api: If True, the environment will use the new gym api standard for
+                step and reset methods.
+        """
+        # super(StockEnv, self).__init__()
+        # money = 10 , scope = 1
+        self._time_window = time_window
+        self._time_index = time_window - 1
+        self._time_column = time_column
+        self._time_format = time_format
+        self._tic_column = tic_column
+        self._df = df
+        self._initial_amount = initial_amount
+        self._return_last_action = return_last_action
+        self._reward_scaling = reward_scaling
+        self._comission_fee_pct = comission_fee_pct
+        self._comission_fee_model = comission_fee_model
+        self._features = features
+        self._valuation_feature = valuation_feature
+        self._cwd = Path(cwd)
+        self._new_gym_api = new_gym_api
+
+        # results file
+        self._results_file = self._cwd / "results" / "rl"
+        self._results_file.mkdir(parents=True, exist_ok=True)
+
+        # price variation
+        self._df_price_variation = None
+
+        # preprocess data
+        self._preprocess_data(order_df, normalize_df)
+
+        # dims and spaces
+        self._tic_list = self._df[self._tic_column].unique()
+        self.portfolio_size = len(self._tic_list)
+        action_space = 1 + self.portfolio_size
+
+        # sort datetimes and define episode length
+        self._sorted_times = sorted(set(self._df[time_column]))
+        self.episode_length = len(self._sorted_times) - time_window + 1
+
+        # define action space
+        self.action_space = spaces.Box(low=0, high=1, shape=(action_space,))
+
+        # define observation state
+        if self._return_last_action:
+            # if  last action must be returned, a dict observation
+            # is defined
+            self.observation_space = spaces.Dict(
+                {
+                    "state": spaces.Box(
+                        low=-np.inf,
+                        high=np.inf,
+                        shape=(
+                            len(self._features),
+                            self.portfolio_size,
+                            self._time_window,
+                        ),
+                    ),
+                    "last_action": spaces.Box(low=0, high=1, shape=(action_space,)),
+                }
+            )
+        else:
+            # if information about last action is not relevant,
+            # a 3D observation space is defined
+            self.observation_space = spaces.Box(
+                low=-np.inf,
+                high=np.inf,
+                shape=(len(self._features), self.portfolio_size, self._time_window),
+            )
+
+        self._reset_memory()
+
+        self._portfolio_value = self._initial_amount
+        self._terminal = False
+
+    def step(self, actions):
+        """Performs a simulation step.
+
+        Args:
+            actions: An unidimensional array containing the new portfolio
+                weights.
+
+        Note:
+            If the environment was created with "return_last_action" set to
+            True, the next state returned will be a Dict. If it's set to False,
+            the next state will be a Box. You can check the observation state
+            through the attribute "observation_space".
+
+        Returns:
+            If "new_gym_api" is set to True, the following tuple is returned:
+            (state, reward, terminal, truncated, info). If it's set to False,
+            the following tuple is returned: (state, reward, terminal, info).
+
+            state: Next simulation state.
+            reward: Reward related to the last performed action.
+            terminal: If True, the environment is in a terminal state.
+            truncated: If True, the environment has passed it's simulation
+                time limit. Currently, it's always False.
+            info: A dictionary containing informations about the last state.
+        """
+        self._terminal = self._time_index >= len(self._sorted_times) - 1
+
+        if self._terminal:
+            metrics_df = pd.DataFrame(
+                {
+                    "date": self._date_memory,
+                    "returns": self._portfolio_return_memory,
+                    "rewards": self._portfolio_reward_memory,
+                    "portfolio_values": self._asset_memory["final"],
+                }
+            )
+            metrics_df.set_index("date", inplace=True)
+
+            plt.plot(metrics_df["portfolio_values"], "r")
+            plt.title("Portfolio Value Over Time")
+            plt.xlabel("Time")
+            plt.ylabel("Portfolio value")
+            plt.savefig(self._results_file / "portfolio_value.png")
+            plt.close()
+
+            plt.plot(self._portfolio_reward_memory, "r")
+            plt.title("Reward Over Time")
+            plt.xlabel("Time")
+            plt.ylabel("Reward")
+            plt.savefig(self._results_file / "reward.png")
+            plt.close()
+
+            plt.plot(self._actions_memory)
+            plt.title("Actions performed")
+            plt.xlabel("Time")
+            plt.ylabel("Weight")
+            plt.savefig(self._results_file / "actions.png")
+            plt.close()
+
+            print("=================================")
+            print("Initial portfolio value:{}".format(self._asset_memory["final"][0]))
+            print(f"Final portfolio value: {self._portfolio_value}")
+            print(
+                "Final accumulative portfolio value: {}".format(
+                    self._portfolio_value / self._asset_memory["final"][0]
+                )
+            )
+            print(
+                "Maximum DrawDown: {}".format(
+                    qs.stats.max_drawdown(metrics_df["portfolio_values"])
+                )
+            )
+            print("Sharpe ratio: {}".format(qs.stats.sharpe(metrics_df["returns"])))
+            print("=================================")
+
+            qs.plots.snapshot(
+                metrics_df["returns"],
+                show=False,
+                savefig=self._results_file / "portfolio_summary.png",
+            )
+
+            if self._new_gym_api:
+                return self._state, self._reward, self._terminal, False, self._info
+            return self._state, self._reward, self._terminal, self._info
+
+        else:
+            # transform action to numpy array (if it's a list)
+            actions = np.array(actions, dtype=np.float32)
+
+            # if necessary, normalize weights
+            if math.isclose(np.sum(actions), 1, abs_tol=1e-6) and np.min(actions) >= 0:
+                weights = actions
+            else:
+                weights = self._softmax_normalization(actions)
+
+            # save initial portfolio weights for this time step
+            self._actions_memory.append(weights)
+
+            # get last step final weights and portfolio_value
+            last_weights = self._final_weights[-1]
+
+            # load next state
+            self._time_index += 1
+            self._state, self._info = self._get_state_and_info_from_time_index(
+                self._time_index
+            )
+
+            # if using weights vector modifier, we need to modify weights vector
+            if self._comission_fee_model == "wvm":
+                delta_weights = weights - last_weights
+                delta_assets = delta_weights[1:]  # disconsider
+                # calculate fees considering weights modification
+                fees = np.sum(np.abs(delta_assets * self._portfolio_value))
+                if fees > weights[0] * self._portfolio_value:
+                    weights = last_weights
+                    # maybe add negative reward
+                else:
+                    portfolio = weights * self._portfolio_value
+                    portfolio[0] -= fees
+                    self._portfolio_value = np.sum(portfolio)  # new portfolio value
+                    weights = portfolio / self._portfolio_value  # new weights
+            elif self._comission_fee_model == "trf":
+                last_mu = 1
+                mu = 1 - 2 * self._comission_fee_pct + self._comission_fee_pct**2
+                while abs(mu - last_mu) > 1e-10:
+                    last_mu = mu
+                    mu = (
+                        1
+                        - self._comission_fee_pct * weights[0]
+                        - (2 * self._comission_fee_pct - self._comission_fee_pct**2)
+                        * np.sum(np.maximum(last_weights[1:] - mu * weights[1:], 0))
+                    ) / (1 - self._comission_fee_pct * weights[0])
+                self._info["trf_mu"] = mu
+                self._portfolio_value = mu * self._portfolio_value
+
+            # save initial portfolio value of this time step
+            self._asset_memory["initial"].append(self._portfolio_value)
+
+            # time passes and time variation changes the portfolio distribution
+            portfolio = self._portfolio_value * (weights * self._price_variation)
+
+            # calculate new portfolio value and weights
+            self._portfolio_value = np.sum(portfolio)
+            weights = portfolio / self._portfolio_value
+
+            # save final portfolio value and weights of this time step
+            self._asset_memory["final"].append(self._portfolio_value)
+            self._final_weights.append(weights)
+
+            # save date memory
+            self._date_memory.append(self._info["end_time"])
+
+            # define portfolio return
+            rate_of_return = (
+                self._asset_memory["final"][-1] / self._asset_memory["final"][-2]
+            )
+            portfolio_return = rate_of_return - 1
+            portfolio_reward = np.log(rate_of_return)
+
+            # save portfolio return memory
+            self._portfolio_return_memory.append(portfolio_return)
+            self._portfolio_reward_memory.append(portfolio_reward)
+
+            # Define portfolio return
+            self._reward = portfolio_reward
+            self._reward = self._reward * self._reward_scaling
+
+        if self._new_gym_api:
+            return self._state, self._reward, self._terminal, False, self._info
+        return self._state, self._reward, self._terminal, self._info
+
+    def reset(self):
+        """Resets the environment and returns it to its initial state (the
+        fist date of the dataframe).
+
+        Note:
+            If the environment was created with "return_last_action" set to
+            True, the initial state will be a Dict. If it's set to False,
+            the initial state will be a Box. You can check the observation
+            state through the attribute "observation_space".
+
+        Returns:
+            If "new_gym_api" is set to True, the following tuple is returned:
+            (state, info). If it's set to False, only the initial state is
+            returned.
+
+            state: Initial state.
+            info: Initial state info.
+        """
+        # time_index must start a little bit in the future to implement lookback
+        self._time_index = self._time_window - 1
+        self._reset_memory()
+
+        self._state, self._info = self._get_state_and_info_from_time_index(
+            self._time_index
+        )
+        self._portfolio_value = self._initial_amount
+        self._terminal = False
+
+        if self._new_gym_api:
+            return self._state, self._info
+        return self._state
+
+    def _get_state_and_info_from_time_index(self, time_index):
+        """Gets state and information given a time index. It also updates "data"
+        attribute with information about the current simulation step.
+
+        Args:
+            time_index: An integer that represents the index of a specific datetime.
+                The initial datetime of the dataframe is given by 0.
+
+        Note:
+            If the environment was created with "return_last_action" set to
+            True, the returned state will be a Dict. If it's set to False,
+            the returned state will be a Box. You can check the observation
+            state through the attribute "observation_space".
+
+        Returns:
+            A tuple with the following form: (state, info).
+
+            state: The state of the current time index. It can be a Box or a Dict.
+            info: A dictionary with some informations about the current simulation
+                step. The dict has the following keys::
+
+                {
+                "tics": List of ticker symbols,
+                "start_time": Start time of current time window,
+                "start_time_index": Index of start time of current time window,
+                "end_time": End time of current time window,
+                "end_time_index": Index of end time of current time window,
+                "data": Data related to the current time window,
+                "price_variation": Price variation of current time step
+                }
+        """
+        # returns state in form (channels, tics, timesteps)
+        end_time = self._sorted_times[time_index]
+        start_time = self._sorted_times[time_index - (self._time_window - 1)]
+
+        # define data to be used in this time step
+        self._data = self._df[
+            (self._df[self._time_column] >= start_time)
+            & (self._df[self._time_column] <= end_time)
+        ][[self._time_column, self._tic_column] + self._features]
+
+        # define price variation of this time_step
+        self._price_variation = self._df_price_variation[
+            self._df_price_variation[self._time_column] == end_time
+        ][self._valuation_feature].to_numpy()
+        self._price_variation = np.insert(self._price_variation, 0, 1)
+
+        # define state to be returned
+        state = None
+        for tic in self._tic_list:
+            tic_data = self._data[self._data[self._tic_column] == tic]
+            tic_data = tic_data[self._features].to_numpy().T
+            tic_data = tic_data[..., np.newaxis]
+            state = tic_data if state is None else np.append(state, tic_data, axis=2)
+        state = state.transpose((0, 2, 1))
+        info = {
+            "tics": self._tic_list,
+            "start_time": start_time,
+            "start_time_index": time_index - (self._time_window - 1),
+            "end_time": end_time,
+            "end_time_index": time_index,
+            "data": self._data,
+            "price_variation": self._price_variation,
+        }
+        return self._standardize_state(state), info
+
+    def render(self, mode="human"):
+        """Renders the environment.
+
+        Returns:
+            Observation of current simulation step.
+        """
+        return self._state
+
+    def _softmax_normalization(self, actions):
+        """Normalizes the action vector using softmax function.
+
+        Returns:
+            Normalized action vector (portfolio vector).
+        """
+        numerator = np.exp(actions)
+        denominator = np.sum(np.exp(actions))
+        softmax_output = numerator / denominator
+        return softmax_output
+
+    def enumerate_portfolio(self):
+        """Enumerates the current porfolio by showing the ticker symbols
+        of all the investments considered in the portfolio.
+        """
+        print("Index: 0. Tic: Cash")
+        for index, tic in enumerate(self._tic_list):
+            print(f"Index: {index + 1}. Tic: {tic}")
+
+    def _preprocess_data(self, order, normalize):
+        """Orders and normalizes the environment's dataframe.
+
+        Args:
+            order: If true, the dataframe will be ordered by ticker list
+                and datetime.
+            normalize: Defines the normalization method applied to the dataframe.
+                Possible values are "by_previous_time", "by_fist_time_window_value",
+                "by_COLUMN_NAME" (where COLUMN_NAME must be changed to a real column
+                name) and a custom function. If None no normalization is done.
+        """
+        # order time dataframe by tic and time
+        if order:
+            self._df = self._df.sort_values(by=[self._tic_column, self._time_column])
+        # defining price variation after ordering dataframe
+        self._df_price_variation = self._temporal_variation_df()
+        # apply normalization
+        if normalize:
+            self._normalize_dataframe(normalize)
+        # transform str to datetime
+        self._df[self._time_column] = pd.to_datetime(self._df[self._time_column])
+        self._df_price_variation[self._time_column] = pd.to_datetime(
+            self._df_price_variation[self._time_column]
+        )
+        # transform numeric variables to float32 (compatibility with pytorch)
+        self._df[self._features] = self._df[self._features].astype("float32")
+        self._df_price_variation[self._features] = self._df_price_variation[
+            self._features
+        ].astype("float32")
+
+    def _reset_memory(self):
+        """Resets the environment's memory."""
+        date_time = self._sorted_times[self._time_index]
+        # memorize portfolio value each step
+        self._asset_memory = {
+            "initial": [self._initial_amount],
+            "final": [self._initial_amount],
+        }
+        # memorize portfolio return and reward each step
+        self._portfolio_return_memory = [0]
+        self._portfolio_reward_memory = [0]
+        # initial action: all money is allocated in cash
+        self._actions_memory = [
+            np.array([1] + [0] * self.portfolio_size, dtype=np.float32)
+        ]
+        # memorize portfolio weights at the ending of time step
+        self._final_weights = [
+            np.array([1] + [0] * self.portfolio_size, dtype=np.float32)
+        ]
+        # memorize datetimes
+        self._date_memory = [date_time]
+
+    def _standardize_state(self, state):
+        """Standardize the state given the observation space. If "return_last_action"
+        is set to False, a three-dimensional box is returned. If it's set to True, a
+        dictionary is returned. The dictionary follows the standard below::
+
+            {
+            "state": Three-dimensional box representing the current state,
+            "last_action": One-dimensional box representing the last action
+            }
+        """
+        last_action = self._actions_memory[-1]
+        if self._return_last_action:
+            return {"state": state, "last_action": last_action}
+        else:
+            return state
+
+    def _normalize_dataframe(self, normalize):
+        """ "Normalizes the environment's dataframe.
+
+        Args:
+            normalize: Defines the normalization method applied to the dataframe.
+                Possible values are "by_previous_time", "by_fist_time_window_value",
+                "by_COLUMN_NAME" (where COLUMN_NAME must be changed to a real column
+                name) and a custom function. If None no normalization is done.
+
+        Note:
+            If a custom function is used in the normalization, it must have an
+            argument representing the environment's dataframe.
+        """
+        if type(normalize) == str:
+            if normalize == "by_fist_time_window_value":
+                print(
+                    "Normalizing {} by first time window value...".format(
+                        self._features
+                    )
+                )
+                self._df = self._temporal_variation_df(self._time_window - 1)
+            elif normalize == "by_previous_time":
+                print(f"Normalizing {self._features} by previous time...")
+                self._df = self._temporal_variation_df()
+            elif normalize.startswith("by_"):
+                normalizer_column = normalize[3:]
+                print(f"Normalizing {self._features} by {normalizer_column}")
+                for column in self._features:
+                    self._df[column] = self._df[column] / self._df[normalizer_column]
+        elif callable(normalize):
+            print("Applying custom normalization function...")
+            self._df = normalize(self._df)
+        else:
+            print("No normalization was performed.")
+
+    def _temporal_variation_df(self, periods=1):
+        """Calculates the temporal variation dataframe. For each feature, this
+        dataframe contains the rate of the current feature's value and the last
+        feature's value given a period. It's used to normalize the dataframe.
+
+        Args:
+            periods: Periods (in time indexes) to calculate temporal variation.
+
+        Returns:
+            Temporal variation dataframe.
+        """
+        df_temporal_variation = self._df.copy()
+        prev_columns = []
+        for column in self._features:
+            prev_column = f"prev_{column}"
+            prev_columns.append(prev_column)
+            df_temporal_variation[prev_column] = df_temporal_variation.groupby(
+                self._tic_column
+            )[column].shift(periods=periods)
+            df_temporal_variation[column] = (
+                df_temporal_variation[column] / df_temporal_variation[prev_column]
+            )
+        df_temporal_variation = (
+            df_temporal_variation.drop(columns=prev_columns)
+            .fillna(1)
+            .reset_index(drop=True)
+        )
+        return df_temporal_variation
+
+    def _seed(self, seed=None):
+        """Seeds the sources of randomness of this environment to guarantee
+        reproducibility.
+
+        Args:
+            seed: Seed value to be applied.
+
+        Returns:
+            Seed value applied.
+        """
+        self.np_random, seed = seeding.np_random(seed)
+        return [seed]
+
+    def get_sb_env(self, env_number=1):
+        """Generates an environment compatible with Stable Baselines 3. The
+        generated environment is a vectorized version of the current one.
+
+        Returns:
+            A tuple with the generated environment and an initial observation.
+        """
+        e = DummyVecEnv([lambda: self] * env_number)
+        obs = e.reset()
+        return e, obs