Farama Foundation

All

50 repositories

MPE2
Public
A set of communication oriented environments
Python
•
MIT License
•15•28•4•4•Updated Mar 3, 2026Mar 3, 2026
Gymnasium
Public
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
api reinforcement-learning gym
Python
•
MIT License
•1.3k•11k•75•10•Updated Mar 3, 2026Mar 3, 2026
Arcade-Learning-Environment
Public
The Arcade Learning Environment (ALE) -- a platform for AI research.
C++
•
GNU General Public License v2.0
•461•2.4k•33•11•Updated Mar 3, 2026Mar 3, 2026
farama.org
Public
HTML
•7•5•0•1•Updated Mar 3, 2026Mar 3, 2026
stable-retro
Public
Retro games for Reinforcement Learning Research
machine-learning research reinforcement-learning retro videogames gymnasium
C++
•
MIT License
•66•352•3•8•Updated Mar 2, 2026Mar 2, 2026
Minigrid
Public
Simple and easily configurable grid world environments for reinforcement learning
gym gridworld-environment
Python
•
Other
•640•2.4k•19•11•Updated Mar 2, 2026Mar 2, 2026
Miniworld
Public
Simple and easily configurable 3D FPS-game-like environments for reinforcement learning
Python
•
Apache License 2.0
•146•756•2•6•Updated Mar 2, 2026Mar 2, 2026
ViZDoom
Public
Reinforcement Learning environments based on the 1993 game Doom :godmode:
python reinforcement-learning deep-learning examples doom vizdoom gymnasium gym-environment
C++
•430•2k•23•8•Updated Feb 27, 2026Feb 27, 2026
HighwayEnv
Public
A minimalist environment for decision-making in autonomous driving
reinforcement-learning autonomous-driving gym-environment
Python
•
MIT License
•857•3.2k•73•6•Updated Feb 26, 2026Feb 26, 2026
MO-Gymnasium
Public
Multi-objective Gymnasium environments for reinforcement learning
reinforcement-learning gym multi-objective gymnasium gym-environments morl multi-objective-rl
Python
•
MIT License
•52•370•2•3•Updated Feb 11, 2026Feb 11, 2026
PettingZoo
Public
An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
api reinforcement-learning gym gymnasium multiagent-reinforcement-learning multi-agent-reinforcement-learning
Python
•
Other
•474•3.3k•44•15•Updated Feb 6, 2026Feb 6, 2026
Gymnasium-Robotics
Public
A collection of robotics simulation environments for reinforcement learning
reinforcement-learning robotics simulation gymnasium mujoco d4rl
Python
•
MIT License
•133•861•17•9•Updated Jan 24, 2026Jan 24, 2026
Metaworld
Public
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
multi-task mujoco meta-rl benchmark-environments
Python
•
MIT License
•339•1.8k•3•5•Updated Jan 20, 2026Jan 20, 2026
Minari
Public
A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities
reinforcement-learning datasets gymnasium offline-rl
Python
•
Other
•63•496•19•1•Updated Jan 10, 2026Jan 10, 2026
Shimmy
Public
An API conversion tool for popular external reinforcement learning environments
reinforcement-learning deepmind-lab gymnasium gym-environment deepmind-control-suite
Python
•
MIT License
•24•204•5•5•Updated Dec 15, 2025Dec 15, 2025
MAgent2
Public
An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments
C++
•
MIT License
•57•320•20•3•Updated Nov 16, 2025Nov 16, 2025
a2perf-reliability-metrics
Public
Python
•
Apache License 2.0
•1•0•0•0•Updated Nov 7, 2025Nov 7, 2025
a2perf-code-carbon
Public
Jupyter Notebook
•
MIT License
•1•0•0•0•Updated Nov 7, 2025Nov 7, 2025
A2Perf
Public
A2Perf is a benchmark for evaluating agents on sequential decision problems that are relevant to the real world. This repository contains code for running and e…
Python
•
MIT License
•3•10•0•0•Updated Nov 7, 2025Nov 7, 2025
a2perf-web-nav
Public
HTML
•2•2•0•0•Updated Nov 7, 2025Nov 7, 2025
a2perf-quadruped-locomotion
Public
Python
•
Apache License 2.0
•3•7•0•0•Updated Nov 7, 2025Nov 7, 2025
a2perf-benchmark-submission
Public
Python
•2•1•0•0•Updated Nov 7, 2025Nov 7, 2025
a2perf-circuit-training
Public
Python
•
Apache License 2.0
•1•2•0•0•Updated Nov 7, 2025Nov 7, 2025
momaland
Public
Benchmarks for Multi-Objective Multi-Agent Decision Making
Python
•
GNU General Public License v3.0
•18•117•2•0•Updated Oct 7, 2025Oct 7, 2025
CrowdPlay
Public
A web based platform for collecting human actions in reinforcement learning environments
Jupyter Notebook
•
MIT License
•3•31•1•0•Updated Sep 10, 2025Sep 10, 2025
AutoROM
Public
A tool to automate installing Atari ROMs for the Arcade Learning Environment
Python
•
MIT License
•23•79•6•0•Updated Aug 11, 2025Aug 11, 2025
SuperSuit
Public
A collection of wrappers for Gymnasium and PettingZoo environments (being merged into gymnasium.wrappers and pettingzoo.wrappers
Python
•
Other
•64•491•8•1•Updated Aug 11, 2025Aug 11, 2025
rlay
Public
A relay between Gymnasium and any software
Rust
•
MIT License
•0•11•9•1•Updated Aug 11, 2025Aug 11, 2025
chatarena
Public
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
python natural-language-processing ai artificial-intelligence multi-agent multi-agent-simulation multi-agent-reinforcement-learning gpt-4 large-language-models chatgpt
Python
•
Apache License 2.0
•147•1.5k•5•2•Updated Aug 11, 2025Aug 11, 2025
MicroRTS
Public
A simple and highly efficient RTS-game-inspired environment for reinforcement learning
Java
•
GNU General Public License v3.0
•124•341•3•2•Updated Aug 11, 2025Aug 11, 2025