[](https://pre-commit.com/)
[](https://github.com/psf/black)
<p align="center">
<img src="docs/_static/img/MO-Gymnasium-text_small.png" width="500px"/>
</p>
<!-- start elevator-pitch -->
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](https://github.com/Farama-Foundation/Gymnasium), but return vectorized rewards as numpy arrays.
The documentation website is at [mo-gymnasium.farama.org](https://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.
<!-- end elevator-pitch -->
## Environments
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](https://mo-gymnasium.farama.org/environments/all-environments/).
## Installation
<!-- start install -->
To install MO-Gymnasium, use:
```bash
pip install mo-gymnasium
```
This 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.
<!-- end install -->
## API
<!-- start snippet-usage -->
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:
```python
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.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](https://link.springer.com/article/10.1007/s10458-022-09552-y).
You can also check more examples in this colab notebook! [](https://colab.research.google.com/github/Farama-Foundation/MO-Gymnasium/blob/main/mo_gymnasium_demo.ipynb)
<!-- end snippet-usage -->
## Notable related libraries
[MORL-Baselines](https://github.com/LucasAlegre/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.
## Environment Versioning
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.
## Development Roadmap
We have a roadmap for future development available here: https://github.com/Farama-Foundation/MO-Gymnasium/issues/66.
## Project Maintainers
Project Managers: [Lucas Alegre](https://github.com/LucasAlegre) and [Florian Felten](https://github.com/ffelten).
Maintenance for this project is also contributed by the broader Farama team: [farama.org/team](https://farama.org/team).
## Citing
<!-- start citation -->
If you use this repository in your research, please cite:
```bibtex
@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}
}
```
<!-- end citation -->
Raw data
{
"_id": null,
"home_page": "",
"name": "mo-gymnasium",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "",
"keywords": "Reinforcement Learning,Multi-Objective,RL,AI,gymnasium",
"author": "",
"author_email": "Farama Foundation <contact@farama.org>",
"download_url": "https://files.pythonhosted.org/packages/a5/f0/9716a6569d62dcd968029b63ce95153d783a6ae88444ead81adc206ee64f/mo-gymnasium-1.1.0.tar.gz",
"platform": null,
"description": "\n[](https://pre-commit.com/)\n[](https://github.com/psf/black)\n\n<p align=\"center\">\n <img src=\"docs/_static/img/MO-Gymnasium-text_small.png\" width=\"500px\"/>\n</p>\n\n<!-- start elevator-pitch -->\n\nMO-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](https://github.com/Farama-Foundation/Gymnasium), but return vectorized rewards as numpy arrays.\n\nThe documentation website is at [mo-gymnasium.farama.org](https://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.\n\n<!-- end elevator-pitch -->\n\n## Environments\n\nMO-Gymnasium includes environments taken from the MORL literature, as well as multi-objective version of classical environments, such as MuJoco.\nThe full list of environments is available [here](https://mo-gymnasium.farama.org/environments/all-environments/).\n\n## Installation\n<!-- start install -->\n\nTo install MO-Gymnasium, use:\n```bash\npip install mo-gymnasium\n```\n\nThis 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.\n\n<!-- end install -->\n\n## API\n\n<!-- start snippet-usage -->\n\nAs 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:\n\n```python\nimport gymnasium as gym\nimport mo_gymnasium as mo_gym\nimport numpy as np\n\n# It follows the original Gymnasium API ...\nenv = mo_gym.make('minecart-v0')\n\nobs, info = env.reset()\n# but vector_reward is a numpy array!\nnext_obs, vector_reward, terminated, truncated, info = env.step(your_agent.act(obs))\n\n# Optionally, you can scalarize the reward function with the LinearReward wrapper\nenv = mo_gym.LinearReward(env, weight=np.array([0.8, 0.2, 0.2]))\n```\nFor details on multi-objective MDP's (MOMDP's) and other MORL definitions, see [A practical guide to multi-objective reinforcement learning and planning](https://link.springer.com/article/10.1007/s10458-022-09552-y).\n\nYou can also check more examples in this colab notebook! [](https://colab.research.google.com/github/Farama-Foundation/MO-Gymnasium/blob/main/mo_gymnasium_demo.ipynb)\n\n<!-- end snippet-usage -->\n\n## Notable related libraries\n\n[MORL-Baselines](https://github.com/LucasAlegre/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.\n\n## Environment Versioning\n\nMO-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.\n\n## Development Roadmap\nWe have a roadmap for future development available here: https://github.com/Farama-Foundation/MO-Gymnasium/issues/66.\n\n## Project Maintainers\n\nProject Managers: [Lucas Alegre](https://github.com/LucasAlegre) and [Florian Felten](https://github.com/ffelten).\n\nMaintenance for this project is also contributed by the broader Farama team: [farama.org/team](https://farama.org/team).\n\n## Citing\n\n<!-- start citation -->\n\nIf you use this repository in your research, please cite:\n\n```bibtex\n@inproceedings{felten_toolkit_2023,\n\tauthor = {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}},\n\ttitle = {A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning},\n\tbooktitle = {Proceedings of the 37th Conference on Neural Information Processing Systems ({NeurIPS} 2023)},\n\tyear = {2023}\n}\n```\n\n<!-- end citation -->\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "A standard API for MORL and a diverse set of reference environments.",
"version": "1.1.0",
"project_urls": {
"Bug Report": "https://github.com/Farama-Foundation/MO-Gymnasium/issues",
"Documentation": "https://mo-gymnasium.farama.org",
"Homepage": "https://mo-gymnasium.farama.org",
"Repository": "https://github.com/Farama-Foundation/MO-Gymnasium"
},
"split_keywords": [
"reinforcement learning",
"multi-objective",
"rl",
"ai",
"gymnasium"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "12525566570e1365b9f2b52d4006528bf10ff9bcdd1dbadcd32b29e3cb2a94d8",
"md5": "6259f8d09ad8979019de25ec20791122",
"sha256": "4cef786ce169949b2bc7b714743ed070a2aaefb9498d96aaf26128b937573b09"
},
"downloads": -1,
"filename": "mo_gymnasium-1.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6259f8d09ad8979019de25ec20791122",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 469350,
"upload_time": "2024-03-11T14:38:04",
"upload_time_iso_8601": "2024-03-11T14:38:04.683832Z",
"url": "https://files.pythonhosted.org/packages/12/52/5566570e1365b9f2b52d4006528bf10ff9bcdd1dbadcd32b29e3cb2a94d8/mo_gymnasium-1.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "a5f09716a6569d62dcd968029b63ce95153d783a6ae88444ead81adc206ee64f",
"md5": "8c16eb234c6579ebcc2acf3331e0f34d",
"sha256": "feaee103e33acfacb4f2f0729f83b4905bd2d8e2fca944681395203a30acec89"
},
"downloads": -1,
"filename": "mo-gymnasium-1.1.0.tar.gz",
"has_sig": false,
"md5_digest": "8c16eb234c6579ebcc2acf3331e0f34d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 462780,
"upload_time": "2024-03-11T14:38:06",
"upload_time_iso_8601": "2024-03-11T14:38:06.962071Z",
"url": "https://files.pythonhosted.org/packages/a5/f0/9716a6569d62dcd968029b63ce95153d783a6ae88444ead81adc206ee64f/mo-gymnasium-1.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-03-11 14:38:06",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Farama-Foundation",
"github_project": "MO-Gymnasium",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "mo-gymnasium"
}
JSON
