https://github.com/rickstaa/stable-gym
This package contains several gymnasium environments with positive definite cost functions, designed for compatibility with stable RL agents.
https://github.com/rickstaa/stable-gym
artificial-intelligence gym-environments gymnasium openai-gym reinforcement-learning robustness simulation stability
Last synced: 8 months ago
JSON representation
This package contains several gymnasium environments with positive definite cost functions, designed for compatibility with stable RL agents.
- Host: GitHub
- URL: https://github.com/rickstaa/stable-gym
- Owner: rickstaa
- License: mit
- Created: 2020-08-14T09:56:22.000Z (about 5 years ago)
- Default Branch: main
- Last Pushed: 2024-09-04T23:27:09.000Z (about 1 year ago)
- Last Synced: 2025-02-01T15:23:16.467Z (8 months ago)
- Topics: artificial-intelligence, gym-environments, gymnasium, openai-gym, reinforcement-learning, robustness, simulation, stability
- Language: Python
- Homepage: https://rickstaa.dev/stable-gym
- Size: 31.9 MB
- Stars: 12
- Watchers: 3
- Forks: 2
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Citation: CITATION.cff
Awesome Lists containing this project
README
# Stable Gym
[](https://github.com/rickstaa/stable-gym/actions/workflows/stable_gym.yml)
[](https://github.com/rickstaa/stable-gym/releases)
[](https://www.python.org/)
[](https://codecov.io/gh/rickstaa/stable-gym)
[](CONTRIBUTING.md)
[](https://zenodo.org/badge/latestdoi/287501190)A Python package that contains several [gymnasium environments](https://gymnasium.farama.org/) with positive definite cost functions, designed for compatibility with stable RL agents. It was initially created for the stable RL algorithms in the [Stable Learning Control](https://github.com/rickstaa/stable-learning-control) package but can be used with any RL agent requiring a **positive definite cost function**. For more information about stable RL agents see the [Stable Learning Control documentation](https://rickstaa.dev/stable-learning-control).
## Installation and Usage
Please see the accompanying [documentation](https://rickstaa.dev/stable-gym) for information on installing and using this package.
## Contributing
We use [husky](https://github.com/typicode/husky) pre-commit hooks and github actions to enforce high code quality. Before contributing to this repository, please check the [contribution guidelines](CONTRIBUTING.md).
> \[!NOTE]\
> We used [husky](https://github.com/typicode/husky) instead of [pre-commit](https://pre-commit.com/), which is more commonly used with Python projects. This was done because only some tools we wanted to use were possible to integrate the Please feel free to open a [PR](https://github.com/rickstaa/stable-gym/pulls) if you want to switch to pre-commit if this is no longer the case.