Gymnasium Python Packages

pettingzoo

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

shimmy

An API conversion tool for popular external reinforcement learning 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

gymnasium-robotics

A collection of robotics simulation 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

craftground

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

imitation

Clean PyTorch implementations of imitation and reward learning algorithms

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

stable-retro

Retro games for Reinforcement Learning Research

actorch

Deep reinforcement learning framework for fast prototyping based on PyTorch

sumo-rl

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

crosslearn

Reusable representation extractors for reinforcement learning across vectors, images, and Chronos-backed time-series windows.

rtgym

Easily implement custom Gymnasium environments for real-time applications

pyrddlgym

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

ghostloop

The agent loop, embodied. Tool-using runtime + fail-closed safety pipeline + sim-first execution + statistically-rigorous bench harness + post-hoc analysis (counterfactual replay, causal attribution, LLM judge, property mining) for embodied AI. Sister project to GhostLM.

unienv

Framework unifying robot environments and data APIs

ns-gym

A simulation toolkit for non-stationary Markov decision processes

rddlrepository

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

remoterl

RemoteRL — zero-setup cloud service for reinforcement learning, anywhere and at any scale

deltatau-audit

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

tactile-mnist

The Tactile-MNIST Active Perception Benchmark

parallelcbf

Composable safety-filter and auditability layer for tensor-parallel reinforcement learning. CBF safety filters, watchdog registries, pre-registration artifacts, failure forensics.

gymnasium-sudoku

Gymnasium-based Sudoku environment for reinforcement learning research/experiments