PyRank
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About

Gym Python Packages

Python packages with the GitHub topic gym. Sorted by relevance, with stars and monthly downloads.
Farama-Foundation
gymnasium

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

6.1M 12K 1K
DLR-RM
stable-baselines3

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

1.4M 13K 2K
Farama-Foundation
pettingzoo

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

383K 3K 484
Stable-Baselines-Team
sb3-contrib

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

296K 716 240
open-thought
reasoning-gym

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

137K 1K 119
Toni-SM
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

77K 1K 142
Farama-Foundation
minigrid

Simple and easily configurable grid world environments for reinforcement learning

63K 2K 641
sail-sg
envpool

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

28K 1K 137
axon-rl
gem-llm

A Gym for Agentic LLMs

23K 487 33
Farama-Foundation
gym-minigrid

Simple and easily configurable grid world environments for reinforcement learning

18K 2K 641
Farama-Foundation
mo-gymnasium

Multi-objective Gymnasium environments for reinforcement learning

16K 381 53
DLR-RM
rl-zoo3

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

6K 3K 598
hill-a
stable-baselines

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

4K 4K 726
proroklab
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.

4K 566 109
mpSchrader
gym-sokoban

Sokoban environment for OpenAI Gym

4K 401 90
opendilab
lightzero

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

3K 2K 190
LucasAlegre
sumo-rl

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

3K 1K 261
EMI-Group
evox

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

2K 2K 334
yannbouteiller
rtgym

Easily implement custom Gymnasium environments for real-time applications

2K 103 6
robotology
gym-ignition

Framework for developing OpenAI Gym robotics environments simulated with Ignition Gazebo

2K 251 27
marella
train

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

2K 1 0
ClementPerroud
gym-trading-env

A simple, easy, customizable Gymnasium environment for trading.

2K 491 104
robotology
scenario

Framework for developing OpenAI Gym robotics environments simulated with Ignition Gazebo

2K 251 27
pyrddlgym-project
pyrddlgym

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

1K 93 23
    • Data from PyPI, GitHub, ClickHouse, and BigQuery