Farama Foundation ORG

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

A standard Python toolkit for reinforcement learning that provides a shared API and a large collection of environments, from pole-balancing puzzles to Atari games, so any learning algorithm can plug into any environment with the same ten lines of code.

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

A minimalist environment for decision-making in autonomous driving

Simple and easily configurable grid world environments for reinforcement learning

The Arcade Learning Environment (ALE) -- a platform for AI research.

Reinforcement Learning environments based on the 1993 game Doom :godmode:

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

A collection of reference environments for offline reinforcement learning

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

A collection of robotics simulation environments for reinforcement learning

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

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

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

MiniWoB++: a web interaction benchmark for reinforcement learning

Multi-objective Gymnasium environments for reinforcement learning

Retro games for Reinforcement Learning Research

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

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

A simple and highly efficient RTS-game-inspired environment for reinforcement learning (formerly Gym-MicroRTS)

An API conversion tool for popular external reinforcement learning environments

No description.

An engine to create high performance multi-agent grid world environments with hundreds or thousands of agents, along with a set of reference environments

Benchmarks for Multi-Objective Multi-Agent Decision Making

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

Example code for the Gym documentation

On-the-fly conversions between Jax and NumPy tensors

Code for Gym documentation website

A set of communication oriented environments

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

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

The Arcade Learning Environment (ALE) -- a platform for AI research.

Scripts to recreate the D4RL datasets with Minari

A template gymnasium environment for users to build upon

A small and fast image rescaling library with SIMD support

Procgen2: A community maintained fork of procgen

hanabi_learning_environment is a research platform for Hanabi experiments.

A relay between Gymnasium and any software

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 evaluating participant's submissions on the benchmark platform.

No description.

No description.

No description.

Allows for providing notifications on import to all Farama Packages

No description.

No description.

No description.

No description.

No description.

No description.