Gym Python Packages

gymnasium

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

stable-baselines3

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

reasoning-gym

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

gem-llm

A Gym for Agentic LLMs

sb3-contrib

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

nemo-gym

Evaluate and improve models and agents using environments

skrl

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

envpool

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

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.

train

A library to build and train reinforcement learning agents in OpenAI Gym environments.

gym-sokoban

Sokoban environment for OpenAI Gym

rl-zoo3

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

gym-ignition

Framework for developing OpenAI Gym robotics environments simulated with Ignition Gazebo

lightzero

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

stable-baselines

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

ratinabox

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

liftmath

Offline gym calculator: 1RM with RPE, plate loading and warm-ups, Wilks/DOTS/IPF GL, world records, rest timer. Web app, Android app and Python library.

evox

Distributed GPU-Accelerated Framework for Evolutionary Computation. Comprehensive Library of Evolutionary Algorithms & Benchmark Problems.

scenario

Framework for developing OpenAI Gym robotics environments simulated with Ignition Gazebo

pyrddlgym

A toolkit for auto-generation of OpenAI Gym environments from RDDL description files.

gym-trading-env

A simple, easy, customizable Gymnasium environment for trading.

sailboat-gym

This repository provides a dynamic simulation environment specifically designed for sailboats. With Sailboat Gym, you can explore and experiment with different control algorithms and strategies in a realistic virtual sailing environment.

sumo-rl

Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with Gymnasium, PettingZoo, and popular RL libraries.

numberlink

NumberLink puzzle environment for Gymnasium