PyRank
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About

Reinforcement Learning Python Packages

Python packages with the GitHub topic reinforcement-learning. Sorted by relevance, with stars and monthly downloads.
sgl-project
sglang

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

303.2M 28K 6K
ray-project
ray

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

56.1M 43K 8K
wandb
wandb

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

26.2M 11K 872
Farama-Foundation
gymnasium

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

6.1M 12K 1K
unslothai
unsloth

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

2.2M 65K 6K
pytorch
torchrl

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

1.6M 3K 455
DLR-RM
stable-baselines3

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

1.4M 13K 2K
unslothai
unsloth-zoo

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

1.4M 65K 6K
pytorch
torchtnt

A lightweight library for PyTorch training tools and utilities

1.1M 2K 300
JudgmentLabs
judgeval

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

479K 1K 93
google-deepmind
dm-control

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

471K 5K 752
Farama-Foundation
pettingzoo

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

383K 3K 484
bulletphysics
pybullet

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

358K 14K 3K
sgl-project
sglang-kernel

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

330K 28K 6K
Farama-Foundation
shimmy

An API conversion tool for popular external reinforcement learning environments

320K 209 24
Stable-Baselines-Team
sb3-contrib

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

296K 716 240
sgl-project
sgl-kernel

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

295K 28K 6K
deepmind
open-spiel

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

234K 5K 1K
Future-House
fhlmi

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

166K 134 17
Future-House
fhaviary

A language agent gym with challenging scientific tasks

142K 261 32
ARISE-Initiative
robosuite

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

138K 2K 712
open-thought
reasoning-gym

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

137K 1K 119
Toni-SM
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

77K 1K 142
Future-House
ldp

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

76K 134 17
    • Data from PyPI, GitHub, ClickHouse, and BigQuery