Implementation of the paper Towards mental time travel: a hierarchical memory for reinforcement learning agents using CleanRL.
 Euijin Jeong 💻 |
 Ownfos 💻 |
This project follows the all-contributors specification.
- gym-style BalletEnv reimplementation
- LSTM Agent (+ reconstruct)
- TrXL Agent
- HCAM Agent
We tested on Python 3.10.
We recommand to use Anaconda(or Miniconda) to run in virtual environment.
conda create -n hcam python=3.10 -y
conda activate hcamClone the repo:
git clone https://github.com/jinPrelude/hcam-torch.git
cd hcam-torchInstall poetry and run poetry install. This will install all dependencies we need.
pip install poetry && poetry installIf the installation completed, try ballet_lstm_lang_only.py
# --track for logging wandb.ai
python ballet_lstm_lang_only --trackTested on i9-11900k + RTX 3090 :
| Playing BalletEnv (2_delay16_easy) |
|---|
 |
| Trained in ≈15M total frames | Trained in ≈3H |
|---|---|
 |
 |