从 65,720 个高星开源项目里，
找到你要的下一个。

exercises-dataset 是用 HTML 编写的数据库工具，用于数据存储与查询。

1,324-exercise fitness dataset — animation GIFs, 180×180 thumbnails, muscle-group & equipment data, and step-by-step instructions in 6 languages. Th…

stable-baselines3 是用 Python 编写的学习资料，用于系统学习与查阅，主打适合生产环境。

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

Gymnasium 是用 Python 编写的学习资料，用于系统学习与查阅。

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

openGym 是用 JavaScript 编写的运维工具，用于部署、编排与监控，主打支持自托管。

Self-hosted gym & body-weight tracker — plan routines, log workouts (supersets, warm-ups, cardio), see which muscles are trained, fatigued or detrai…

cleanrl 是用 Python 编写的学习资料，用于系统学习与查阅。

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

workout-cool 是用 TypeScript 编写的数据库工具，用于数据存储与查询，主打功能完整、现代化、开源免费。

🏋 Modern open-source fitness coaching platform. Create workout plans, track progress, and access a comprehensive exercise database.

wger 是用 Python 编写的可自托管服务，可以部署在自己的服务器上，主打支持自托管。

Self hosted FLOSS fitness/workout, nutrition and weight tracker

rl-baselines3-zoo 是用 Python 编写的学习资料，用于系统学习与查阅，主打适合生产环境。

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

muzero-general 是用 Python 编写的学习资料，用于系统学习与查阅。

MuZero

evox 是用 Python 编写的学习资料，用于系统学习与查阅，主打功能完整、可伸缩。

Distributed GPU-Accelerated Framework for Evolutionary Computation. Comprehensive Library of Evolutionary Algorithms & Benchmark Problems.

gym-pybullet-drones 是用 Python 编写的学习资料，用于系统学习与查阅。

PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control

LightZero 是用 Python 编写的学习资料，用于系统学习与查阅。

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

envpool 是用 C++ 编写的学习资料，用于系统学习与查阅，主打高性能。

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

reasoning-gym 是用 Python 编写的学习资料，用于系统学习与查阅。

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

CORL 是用 Python 编写的学习资料，用于系统学习与查阅。

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, S…

Super-mario-bros-PPO-pytorch 是用 Python 编写的 AI 工具，用于大模型与智能体应用开发。

Proximal Policy Optimization (PPO) algorithm for Super Mario Bros

Gym 是用 Python 编写的学习资料，用于系统学习与查阅。

Evaluate and improve models and agents using environments

rl-baselines-zoo 是用 Python 编写的 AI 工具，用于大模型与智能体应用开发，主打适合生产环境。

A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.

Super-mario-bros-A3C-pytorch 是用 Python 编写的学习资料，用于系统学习与查阅，主打异步并发。

Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros

skrl 是用 Python 编写的学习资料，用于系统学习与查阅，主打实现清晰。

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo …

sumo-rl 是用 Python 编写的学习资料，用于系统学习与查阅。

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

rl-book 是用 HTML 编写的学习资料，用于系统学习与查阅。

Source codes for the book "Reinforcement Learning: Theory and Python Implementation"