Projects

If you're interested in submitting a project to us, you can read more here. If you'd like to get involved in contributing, the best way is to join our discord server.

Core

Libraries that provide standard APIs that are reused by other projects within Farama and the community
Gymnasium
Gymnasium

A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

PettingZoo
PettingZoo

A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities

Minari
Minari

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

Mature

Maintained projects that comply with our standards
Minigrid
Minigrid

Simple and easily configurable grid world environments for reinforcement learning

SuperSuit
SuperSuit

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

Gymnasium-Robotics
Gymnasium-Robotics

A collection of robotics simulation environments for reinforcement learning

MAgent2
MAgent2

An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments

Miniworld
Miniworld

Simple and easily configurable 3D FPS-game-like environments for reinforcement learning

MiniWoB++
MiniWoB++

A collection of reinforcement learning environments for simple web interaction tasks

Tinyscaler
Tinyscaler

A small and fast image rescaling library with SIMD support

AutoROM
AutoROM

A tool to automate installing Atari ROMs for the Arcade Learning Environment

Jumpy
Jumpy

On-the-fly conversions between Jax and NumPy tensors

Shimmy
Shimmy

PettingZoo and Gymnasium bindings for popular reinforcement learning environments outside of Farama

MO-Gymnasium
MO-Gymnasium

Multi-objective Gymnasium environments for reinforcement learning

Incubating

Projects we're still actively working to bring up to our standards, debug, and/or create
Arcade Learning Environment
Arcade Learning Environment

A simple framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games

D4RL
D4RL

A collection of reference environments for offline reinforcement learning

MicroRTS
MicroRTS

A simple and highly efficient RTS-game-inspired environment for reinforcement learning

Procgen2
Procgen2

Fast and procedurally generated side-scroller-game-like graphical environments (formerly Procgen)

ViZDoom
ViZDoom

Reinforcement Learning environments based on the 1993 game Doom

Metaworld
Metaworld

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

CrowdPlay
CrowdPlay

A web based platform for collecting human actions in reinforcement learning environments

HighwayEnv
HighwayEnv

A collection of environments for autonomous driving and tactical decision-making tasks

Stable-Retro
Stable-Retro

A fork of gym-retro with additional games, emulators and supported platforms

ChatArena
ChatArena

A multi-agent language game environments for LLMs