Gymnasium Python Packages

pettingzoo

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

shimmy

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

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

minari

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

minigrid

Simple and easily configurable grid world environments for reinforcement learning

gymnasium-robotics

A collection of robotics simulation environments for reinforcement learning

nes-py

Native C++ NES emulator with Python/Gymnasium APIs, vector execution, and cross-platform packaging.

mo-gymnasium

Multi-objective Gymnasium environments for reinforcement learning

datenwissenschaften

Training engine where the Laya decision model learns to beat retro games: text game state, group-relative policy gradients, per-state checkpoints and a reverse curriculum.

tradefloor

A simulated stock market for testing trading strategies and AI agents. Orders move prices, any market can be forked, and every run reproduces exactly.

wickra-gym

A Gymnasium-compatible, microstructure-aware backtest environment with O(1) steps: precompute the dataset to a fixed feature tensor once, then step() is a pure array index. Deterministic RL rollouts, recomputable byte-for-byte in ten languages.

craftground

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

gym-super-mario-bros

Gymnasium environments for NES Mario games, with task metadata, reward instrumentation, and reproducible evaluation interfaces.

stable-retro

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

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。)

twistypuzzle

A Simulator of Twisty Puzzles

gym-minigrid

Simple and easily configurable grid world environments for reinforcement learning

env-breakoutatari2600-turbo-native

🕹️ Reproducible Breakout for parallel RL experiments ⚡

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

imitation

Clean PyTorch implementations of imitation and reward learning algorithms

actorch

Deep reinforcement learning framework for fast prototyping based on PyTorch

linkgym

A reinforcement learning (Gymnasium) environment for 5G NR link adaptation on NVIDIA Sionna, with 3GPP and ray-traced channels, classical baselines and a reproducible evaluation protocol.

pretium

A simulated stock market for testing trading strategies and AI agents. Orders move prices, any market can be forked, and every run reproduces exactly.

masa-safe-rl

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