A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities
Simple and easily configurable grid world environments for reinforcement learning
A collection of wrappers for Gymnasium and PettingZoo environments (being merged into gymnasium.wrappers and pettingzoo.wrappers)
A collection of robotics simulation environments for reinforcement learning
An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments
Simple and easily configurable 3D FPS-game-like environments for reinforcement learning
A collection of reinforcement learning environments for simple web interaction tasks
On-the-fly conversions between Jax and NumPy tensors
PettingZoo and Gymnasium bindings for popular reinforcement learning environments outside of Farama
Multi-objective Gymnasium environments for reinforcement learning
A simple framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games
Fast and procedurally generated side-scroller-game-like graphical environments (formerly Procgen)
Reinforcement Learning environments based on the 1993 game Doom
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
A web based platform for collecting human actions in reinforcement learning environments
A collection of environments for autonomous driving and tactical decision-making tasks
A fork of gym-retro with additional games, emulators and supported platforms
A multi-agent language game environments for LLMs
Multi-objective multi-agent API and environments.
A benchmark for evaluating agents on sequential decision problems that are relevant to the real-world