Gymnasium Python Packages

shimmy

PettingZoo and Gymnasium bindings for popular reinforcement learning environments outside of Farama

pettingzoo

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

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

minigrid

Simple and easily configurable grid world environments for reinforcement learning

gymnasium-robotics

A collection of robotics simulation environments for reinforcement learning

gym-minigrid

Simple and easily configurable grid world environments for reinforcement learning

minari

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

mo-gymnasium

Multi-objective Gymnasium environments for reinforcement learning

stable-retro-turbo

🚀 Blazing-fast Stable Retro fork with native vectorization and preprocessing 🚀

craftground

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

stable-retro

A fork of gym-retro with additional games, emulators and supported platforms

imitation

Clean PyTorch implementations of imitation and reward learning algorithms

axon-quant

AI-native event-driven trading engine. Rust core with Python RL bindings. Built-in Gymnasium environments, LLM agents, SHAP explainability, and model ensembling — from backtesting to production.(AI 原生事件驱动交易引擎，Rust 内核，Python RL 绑定，支持 Gymnasium 环境、LLM 智能体、SHAP 可解释性与模型集成，贯穿回测到生产部署。)

nextstat

Universal differentiable statistical inference engine (Rust + GPU). High-performance Frequentist & Bayesian modeling, RL environments, and end-to-end optimization for Science, Pharma, and Finance

masa-safe-rl

MASA-Safe-RL: A safe reinforcement library for providing a common interface for different constraints and environments

tep-studio

TEP Studio — a schema-driven Python simulator for the modified Tennessee Eastman Process (fixed-step RK4 integrator, decentralized control, Gymnasium env, dataset tooling, web Studio).

pyrddlgym

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

rlox

Rust-accelerated reinforcement learning — 22 algorithms, 2-10x faster than SB3. The Polars of RL.

rddlrepository

Hosts domain and instance RDDL files, covering problems from a wide range of disciplines, integration with the pyRDDLGym ecosystem.

actorch

Deep reinforcement learning framework for fast prototyping based on PyTorch

causalrl

Causal reinforcement learning, organized around Bareinboim's 9-task taxonomy, confounded offline→online RL, POMIS, counterfactual policies, transportability, discovery, imitation, curricula.

morl-baselines

Multi-Objective Reinforcement Learning algorithms implementations.

gymnasium-sudoku

Gymnasium-based Sudoku environment for reinforcement learning research/experiments

deltatau-audit

Time Robustness Audit for RL agents — measures timing reliance, deployment robustness, and stress resilience