Gym Environment Python Packages

shimmy

An API conversion tool for popular external reinforcement learning environments

craftground

⚡⚡ Lightning Fast (~300TPS) Reinforcement Learning environment on latest Minecraft 🏝️

highway-env

A minimalist environment for decision-making in autonomous driving

rlcard

Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.

vmas

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

pogema

[ICLR-2025] POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically designed to be flexible, tunable and scalable. It can be tailored to a variety of PO-MAPF / MAPF settings.

gym-trading-env

A simple, easy, customizable Open IA Gym environments for trading.

rlgym

A Gym-like environment for Reinforcement Learning in Rocket League

ratinabox

A python package for simulating movement and spatial cell types (e.g. place cells, grid cells) in continuous environments.

rtgym

Easily implement custom Gymnasium environments for real-time applications

tactics2d

Tactics2D: A Reinforcement Learning Environment Library with Generative Scenarios for Driving Decision-making

rlgym-api

A Gym-like environment for Reinforcement Learning in Rocket League

memory-gym

A gym that contains the memory benchmarks Mortar Mayhem, Mystery Maze and Searing Spotlights

rlgym-rocket-league

A Gym-like environment for Reinforcement Learning in Rocket League

gymnasium-sudoku

A Sudoku environment for Reinforcement Learning research

evogym

Evolution Gym: A benchmark for developing and evaluating soft robot co-design algorithms.

gym-electric-motor

A Farama Gymnasium environment for electric motor control.

loopquest

A Production Tool for Embodied AI

nemo-gym

NeMo Gym is a library for building reinforcement learning environments

highrl

A library for training robots using RL under the scheme of multi-level RL.

gym-md

MiniDungeons for OpenAI Gym

tile-match-gym

Tile matching gym environment for reinforcement learning research.

drlkit

A High Level Python Deep Reinforcement Learning library. Great for beginners, for prototyping and quickly comparing algorithms

generals

Develop your agent for generals.io!