从 65,729 个高星开源项目里，
找到你要的下一个。

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

Implementations of IQL, QMIX, VDN, COMA, QTRAN, MAVEN, CommNet, DyMA-CL, and G2ANet on SMAC, the decentralised micromanagement scenario of StarCraf…

MAgent 是用 Python 编写的学习资料，用于系统学习与查阅。

A Platform for Many-Agent Reinforcement Learning

tnt 是用 Python 编写的学习资料，用于系统学习与查阅，主打轻量。

A lightweight library for PyTorch training tools and utilities

bindsnet 是用 Python 编写的学习资料，用于系统学习与查阅。

Simulation of spiking neural networks (SNNs) using PyTorch.

agibot_x1_train 是用 Python 编写的学习资料，用于系统学习与查阅。

The reinforcement learning training code for AgiBot X1.

TensorFlow2.0-Examples 是用 Jupyter Notebook 编写的 AI 工具，用于人工智能方向的建模与推理，主打易用。

🙄 Difficult algorithm, Simple code.

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

Deep Neuroevolution

NavRL 是用 C++ 编写的学习资料，用于系统学习与查阅。

[IEEE RA-L'25] NavRL: Learning Safe Flight in Dynamic Environments (NVIDIA Isaac/Python/ROS1/ROS2)

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

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

godot_rl_agents 是用 Python 编写的学习资料，用于系统学习与查阅，主打开源免费。

An Open Source package that allows video game creators, AI researchers and hobbyists the opportunity to learn complex behaviors for their Non Player…

Mortal 是用 Rust 编写的学习资料，用于系统学习与查阅，主打速度快。

🚀🀄️ A fast and strong AI for riichi mahjong, powered by Rust and deep reinforcement learning.

AgentEvolver 是用 Python 编写的 AI 工具，用于大模型与智能体应用开发。

AgentEvolver: Towards Efficient Self-Evolving Agent System

hands-on-rl 是用 Jupyter Notebook 编写的学习资料，用于系统学习与查阅，主打开源免费。

Free course that takes you from zero to Reinforcement Learning PRO 🦸🏻‍🦸🏽

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

DRL-code-pytorch 是用 Python 编写的学习资料，用于系统学习与查阅。

Concise pytorch implements of DRL algorithms, including REINFORCE, A2C, DQN, PPO(discrete and continuous), DDPG, TD3, SAC.

walk-these-ways 是用 Python 编写的学习资料，用于系统学习与查阅。

Sim-to-real RL training and deployment tools for the Unitree Go1 robot.

tensor-house 是用 Jupyter Notebook 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 collection of reference Jupyter notebooks and demo AI/ML applications for enterprise use cases: marketing, pricing, supply chain, smart manufactur…

TextWorld 是用 Jupyter Notebook 编写的学习资料，用于系统学习与查阅。

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

ReCall 是用 Python 编写的 AI 工具，用于大模型与智能体应用开发。

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement …

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

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation…

BeautifulAlgorithms.jl 是用 Julia 编写的学习资料，用于系统学习与查阅，主打界面美观、实现清晰。

Concise and beautiful algorithms written in Julia

Personae 是用 Python 编写的学习资料，用于系统学习与查阅。

📈 Personae is a repo of implements and environment of Deep Reinforcement Learning & Supervised Learning for Quantitative Trading.

awesome-model-based-RL 是一个学习资料，用于系统学习与查阅。

A curated list of awesome model based RL resources (continually updated)