Reinforcement Learning Python Packages

sglang

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

ray

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

wandb

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

gymnasium

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

unsloth

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

torchrl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

stable-baselines3

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

unsloth-zoo

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

torchtnt

A lightweight library for PyTorch training tools and utilities

judgeval

The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

dm-control

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

pettingzoo

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

pybullet

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

sglang-kernel

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

shimmy

An API conversion tool for popular external reinforcement learning environments

sb3-contrib

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

sgl-kernel

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

open-spiel

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

fhlmi

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

fhaviary

A language agent gym with challenging scientific tasks

robosuite

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

reasoning-gym

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

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

ldp

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