#5151st of 56 in ML frameworks and libraries
gymnasium
Python API and environment set for reinforcement learning research
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 12.6k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Gymnasium is a Python library that defines a standard environment API (make, reset, step, action and observation spaces) for connecting reinforcement learning algorithms to environments. It ships Classic Control, Box2D, Toy Text, MuJoCo and Atari families. It is the maintained fork of OpenAI's Gym, run by the Farama Foundation.
Who it is for: Researchers and engineers building or benchmarking RL algorithms in Python
Strengths
- Small, uniform env API with terminated and truncated flags
- Environment families install separately via extras like gymnasium[atari] or gymnasium[all]
- Strict -vN environment versioning to keep learning results reproducible
- Third-party environments and libraries (CleanRL, PettingZoo) use the same API
Weaknesses
- Provides environments and an interface only; no RL algorithms included
- Older Gym-based third-party environments may need apply_env_compatibility
- Some environment families are hard to install on certain systems
- Hardware and RAM requirements are not stated in the README
What it needs
- Needs Python
Also in ML frameworks and libraries
See all 56| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 95 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 92 out of 100 |
| #4 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 89 out of 100 |
| #5 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 89 out of 100 |