Reinforcement Learning Python Packages

wandb

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

gymnasium

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

sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

unsloth-zoo

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

unsloth

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

sglang-kernel

SGLang is a high-performance serving framework for large language models and multimodal models.

stable-baselines3

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

pybullet

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

robosuite

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

trajectory-sdk

Practical recipes for adapting benchmarks, training models, and measuring reward with the Trajectory SDK.

reasoning-gym

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

dm-control

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

torchtnt

A lightweight library for PyTorch training tools and utilities

pettingzoo

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

mooncake-transfer-engine-cuda13

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

fhaviary

A language agent gym with challenging scientific tasks

fhlmi

Framework enabling modular interchange of language agents, environments, and optimizers

sb3-contrib

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

ldp

Framework enabling modular interchange of language agents, environments, and optimizers

nemo-gym

Evaluate and improve models and agents using environments

open-spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

textworld

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

shimmy

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