Gymnasium is a Python library that provides a standard API for developing and comparing reinforcement learning algorithms and environments, maintained as an official fork of OpenAI's Gym. It ships with families of reference environments and enforces strict versioning to support reproducible research.
Project overview
As the officially maintained continuation of OpenAI's Gym, Gymnasium addresses the lack of a standard reinforcement learning API by pairing a stable interface with bundled environment families and strict versioning for reproducible results.
Project type
Evaluation & Observability · Infrastructure
Deployment
Refer to project documentation
License
MIT
Best for
Researchers who need a standard API and versioned reference environments for developing and comparing reinforcement learning algorithms reproducibly.
Developers integrating reinforcement learning environments into Python workflows via a pip-installable library.
Key capabilities
Provides simple Python environment classes for creating environment instances and interacting with them from learning algorithms.
Ships families of environments including Classic Control, Box2D, Toy Text, MuJoCo, and Atari for training and evaluating agents.
Maintains strict versioning for reproducibility, with environment names ending in suffixes like -v0.
Provides apply_env_compatibility in gymnasium.make to handle different API versions of third-party environments.
Limitations and risks
Gymnasium does not officially support Windows, though pull requests adding Windows compatibility are accepted.
The base pip install does not include dependencies for all families of environments; users must install the additional dependencies required by specific environment families.
Getting started
Run pip install gymnasium, then use the library in Python. No external services are required for the base installation, and setup is rated easy.
Evidence and sources
README: Gymnasium is an open source Python library for developing and comparing reinforcement learning algorithms by providing a standard API to communicate between learning algorithms an…
README: Gymnasium includes the following families of environments along with a wide variety of third-party environments
README: To install the base Gymnasium library, use `pip install gymnasium` This does not include dependencies for all families of environments (there's a massive number, and some can be p…
README: The 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 "CartPol…
README: We support and test for Python 3.10, 3.11, 3.12, 3.13 and 3.14 on Linux and macOS. We will accept PRs related to Windows, but do not officially support it.
AI Search
Find projects, verify facts, compare options, or turn a complex need into an actionable plan
Try a searchA click only fills the search box; you stay in control