<p align="center">
<img src="https://raw.githubusercontent.com/Farama-Foundation/SuperSuit/master/supersuit-text.png" width="500px"/>
</p>
SuperSuit introduces a collection of small functions which can wrap reinforcement learning environments to do preprocessing ('microwrappers').
We support Gymnasium for single agent environments and PettingZoo for multi-agent environments (both AECEnv and ParallelEnv environments).
Using it with Gymnasium to convert space invaders to have a grey scale observation space and stack the last 4 frames looks like:
```
import gymnasium
from supersuit import color_reduction_v0, frame_stack_v1
env = gymnasium.make('SpaceInvaders-v0')
env = frame_stack_v1(color_reduction_v0(env, 'full'), 4)
```
Similarly, using SuperSuit with PettingZoo environments looks like
```
from pettingzoo.butterfly import pistonball_v0
env = pistonball_v0.env()
env = frame_stack_v1(color_reduction_v0(env, 'full'), 4)
```
**Please note**: Once the planned wrapper rewrite of Gymnasium is complete and the vector API is stabilized, this project will be deprecated and rewritten as part of a new wrappers package in PettingZoo and the vectorized API will be redone, taking inspiration from the functionality currently in Gymnasium.
## Installing SuperSuit
To install SuperSuit from pypi:
```
python3 -m venv env
source env/bin/activate
pip install --upgrade pip
pip install supersuit
```
Alternatively, to install SuperSuit from source, clone this repo, `cd` to it, and then:
```
python3 -m venv env
source env/bin/activate
pip install --upgrade pip
pip install -e .
```
## Citation
If you use this in your research, please cite:
```
@article{SuperSuit,
Title = {SuperSuit: Simple Microwrappers for Reinforcement Learning Environments},
Author = {Terry, J. K and Black, Benjamin and Hari, Ananth},
journal={arXiv preprint arXiv:2008.08932},
year={2020}
}
```
Raw data
{
"_id": null,
"home_page": null,
"name": "SuperSuit",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "Reinforcement Learning, game, RL, AI, gymnasium",
"author": null,
"author_email": "Farama Foundation <contact@farama.org>",
"download_url": "https://files.pythonhosted.org/packages/ba/c5/74e32167c36bef901efa4b6c977711466f1bb1ad83a8fbd4603eee401b2a/supersuit-3.9.3.tar.gz",
"platform": null,
"description": "<p align=\"center\">\n <img src=\"https://raw.githubusercontent.com/Farama-Foundation/SuperSuit/master/supersuit-text.png\" width=\"500px\"/>\n</p>\n\n\nSuperSuit introduces a collection of small functions which can wrap reinforcement learning environments to do preprocessing ('microwrappers').\nWe support Gymnasium for single agent environments and PettingZoo for multi-agent environments (both AECEnv and ParallelEnv environments).\n\n\nUsing it with Gymnasium to convert space invaders to have a grey scale observation space and stack the last 4 frames looks like:\n\n```\nimport gymnasium\nfrom supersuit import color_reduction_v0, frame_stack_v1\n\nenv = gymnasium.make('SpaceInvaders-v0')\n\nenv = frame_stack_v1(color_reduction_v0(env, 'full'), 4)\n```\n\nSimilarly, using SuperSuit with PettingZoo environments looks like\n\n```\nfrom pettingzoo.butterfly import pistonball_v0\nenv = pistonball_v0.env()\n\nenv = frame_stack_v1(color_reduction_v0(env, 'full'), 4)\n```\n\n\n**Please note**: Once the planned wrapper rewrite of Gymnasium is complete and the vector API is stabilized, this project will be deprecated and rewritten as part of a new wrappers package in PettingZoo and the vectorized API will be redone, taking inspiration from the functionality currently in Gymnasium.\n\n## Installing SuperSuit\nTo install SuperSuit from pypi:\n\n```\npython3 -m venv env\nsource env/bin/activate\npip install --upgrade pip\npip install supersuit\n```\n\nAlternatively, to install SuperSuit from source, clone this repo, `cd` to it, and then:\n\n```\npython3 -m venv env\nsource env/bin/activate\npip install --upgrade pip\npip install -e .\n```\n\n## Citation\n\nIf you use this in your research, please cite:\n\n```\n@article{SuperSuit,\n Title = {SuperSuit: Simple Microwrappers for Reinforcement Learning Environments},\n Author = {Terry, J. K and Black, Benjamin and Hari, Ananth},\n journal={arXiv preprint arXiv:2008.08932},\n year={2020}\n}\n```\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "Wrappers for Gymnasium and PettingZoo",
"version": "3.9.3",
"project_urls": {
"Bug Report": "https://github.com/Farama-Foundation/SuperSuit/issues",
"Homepage": "https://farama.org",
"Repository": "https://github.com/Farama-Foundation/SuperSuit"
},
"split_keywords": [
"reinforcement learning",
" game",
" rl",
" ai",
" gymnasium"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "40aa63ba1c60e15334918abf1991ad1584d2dfc5760b352cba5cb98d61e7ef20",
"md5": "10aaa1234ded2ff4b90b0e63c773177e",
"sha256": "f30ab6fd9fe720ea7fa73d45a96935b6321c4ea1aa45d7997684c09f39aa10de"
},
"downloads": -1,
"filename": "SuperSuit-3.9.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "10aaa1234ded2ff4b90b0e63c773177e",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 50175,
"upload_time": "2024-08-12T16:01:46",
"upload_time_iso_8601": "2024-08-12T16:01:46.149412Z",
"url": "https://files.pythonhosted.org/packages/40/aa/63ba1c60e15334918abf1991ad1584d2dfc5760b352cba5cb98d61e7ef20/SuperSuit-3.9.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "bac574e32167c36bef901efa4b6c977711466f1bb1ad83a8fbd4603eee401b2a",
"md5": "014aa0ee464832be2af2156bf8f21e90",
"sha256": "10f5d0ed208ddb92fba767a7889ada9f46894519077527d6af799a7767a13159"
},
"downloads": -1,
"filename": "supersuit-3.9.3.tar.gz",
"has_sig": false,
"md5_digest": "014aa0ee464832be2af2156bf8f21e90",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 34251,
"upload_time": "2024-08-12T16:01:48",
"upload_time_iso_8601": "2024-08-12T16:01:48.387644Z",
"url": "https://files.pythonhosted.org/packages/ba/c5/74e32167c36bef901efa4b6c977711466f1bb1ad83a8fbd4603eee401b2a/supersuit-3.9.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-08-12 16:01:48",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Farama-Foundation",
"github_project": "SuperSuit",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "supersuit"
}
JSON
