Retro games for 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.

🐍🎮 pygame - Community Edition is a FOSS Python library for multimedia applications (like games). Built on top of the excellent SDL library.

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

A minimalist environment for decision-making in autonomous driving

An API conversion tool for popular external reinforcement learning environments

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

Standard Library

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

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

MiniWoB++: a web interaction benchmark 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 standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

Multi-objective Gymnasium environments for reinforcement learning

Reinforcement Learning environments based on the 1993 game Doom

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

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

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

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

Play lunar lander in you windows file copy dialog

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

The NetHack Learning Environment

Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Procgen2: A community maintained fork of procgen

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

A collection of robotics simulation environments for reinforcement learning

The Ren'Py Visual Novel Engine

A Python interface for reinforcement learning environments