A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym)

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

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

An open source robotics benchmark for meta- and multi-task reinforcement learning

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

MiniWorld: Minimalistic 3D Environment for RL & Robotics Research

Minimalistic gridworld package for OpenAI Gym

An API conversion tool for popular external reinforcement learning environments

PyTorch tutorials.

A conda-smithy repository for ale-py.

Gym for multi-agent reinforcement learning

A minimalist environment for decision-making in autonomous driving

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

A conda-smithy repository for gymnasium.

Multi-objective Gymnasium environments for reinforcement learning

MiniWoB++: a web interaction benchmark for reinforcement learning

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

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

Massively parallel rigidbody physics simulation on accelerator hardware.

A toolkit for developing and comparing reinforcement learning algorithms.