https://github.com/Farama-Foundation/SuperSuit

A collection of wrappers for Gymnasium and PettingZoo environments (being merged into gymnasium.wrappers and pettingzoo.wrappers
https://github.com/Farama-Foundation/SuperSuit

Last synced: 2 months ago
JSON representation

A collection of wrappers for Gymnasium and PettingZoo environments (being merged into gymnasium.wrappers and pettingzoo.wrappers

• Host: GitHub
• URL: https://github.com/Farama-Foundation/SuperSuit
• Owner: Farama-Foundation
• License: other
• Created: 2020-04-01T00:27:34.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2024-09-03T21:34:00.000Z (5 months ago)
• Last Synced: 2024-09-14T07:53:19.754Z (4 months ago)
• Language: Python
• Homepage:
• Size: 1.07 MB
• Stars: 447
• Watchers: 9
• Forks: 56
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

• awesome-production-machine-learning - SuperSuit - Foundation/SuperSuit.svg?style=social) - SuperSuit introduces a collection of small functions which can wrap reinforcement learning environments to do preprocessing ('microwrappers'). (Industry Strength RL)

README

        


    



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}

}

```