MO-Gymnasium is an open source Python library for developing and comparing multi-objective reinforcement learning algorithms by providing a standard API to communicate between learning algorithms and environments, as well as a standard set of environments compliant with that API. Essentially, the environments follow the standard Gymnasium API, but return vectorized rewards as numpy arrays.
The documentation website is at mo-gymnasium.farama.org, and we have a public discord server (which we also use to coordinate development work) that you can join here: https://discord.gg/bnJ6kubTg6.
MO-Gymnasium includes environments taken from the MORL literature, as well as multi-objective version of classical environments, such as MuJoco. The full list of environments is available here.
To install MO-Gymnasium, use:
pip install mo-gymnasiumThis does not include dependencies for all families of environments (some can be problematic to install on certain systems). You can install these dependencies for one family like pip install "mo-gymnasium[mujoco]" or use pip install "mo-gymnasium[all]" to install all dependencies.
As for Gymnasium, the MO-Gymnasium API models environments as simple Python env classes. Creating environment instances and interacting with them is very simple - here's an example using the "minecart-v0" environment:
import gymnasium as gym
import mo_gymnasium as mo_gym
import numpy as np
# It follows the original Gymnasium API ...
env = mo_gym.make('minecart-v0')
obs, info = env.reset()
# but vector_reward is a numpy array!
next_obs, vector_reward, terminated, truncated, info = env.step(your_agent.act(obs))
# Optionally, you can scalarize the reward function with the LinearReward wrapper
env = mo_gym.wrappers.LinearReward(env, weight=np.array([0.8, 0.2, 0.2]))For details on multi-objective MDP's (MOMDP's) and other MORL definitions, see A practical guide to multi-objective reinforcement learning and planning.
You can also check more examples in this colab notebook!
MORL-Baselines is a repository containing various implementations of MORL algorithms by the same authors as MO-Gymnasium. It relies on the MO-Gymnasium API and shows various examples of the usage of wrappers and environments.
MO-Gymnasium keeps strict versioning for reproducibility reasons. All environments end in a suffix like "-v0". When changes are made to environments that might impact learning results, the number is increased by one to prevent potential confusion.
We have a roadmap for future development available here: #66.
Project Managers: Lucas Alegre and Florian Felten.
Maintenance for this project is also contributed by the broader Farama team: farama.org/team.
If you use this repository in your research, please cite:
@inproceedings{felten_toolkit_2023,
author = {Felten, Florian and Alegre, Lucas N. and Now{\'e}, Ann and Bazzan, Ana L. C. and Talbi, El Ghazali and Danoy, Gr{\'e}goire and Silva, Bruno C. {\relax da}},
title = {A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning},
booktitle = {Proceedings of the 37th Conference on Neural Information Processing Systems ({NeurIPS} 2023)},
year = {2023}
}