Simulation verification and physical deployment of robot reinforcement learning algorithms, suitable for quadruped robots, wheeled robots, and humanoid robots. "sar" represents "simulation and real"

对各类图书资源的收集。大量计算机、AI方面书籍。

C++ based gRPC (C++, Python, Ruby, Objective-C, PHP, C#)

Python inverse kinematics based on MuJoCo

[arXiv 2025] GMR: General Motion Retargeting. Retarget human motions into diverse humanoid robots in real time on CPU. Retargeter for TWIST.

Official Code of "VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning"

Vim-fork focused on extensibility and usability

An opensource OpenWrt variant for mainland China users.

A Brushless DC Motor controller board. The design is inspired and is compatible with Odrive project (https://github.com/madcowswe/ODriveHardware) except that this one has a single channel.

High performance motor control

Codebase for Berkeley Humanoid Lite

Model Context Protocol Servers

User-friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...)

程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).

This project aims to enhance the working environment on Windows

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

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, SPOT, Cal-QL, ReBRAC

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

A python library for windows, providing the needed functions to start working on your own with memory editing.

Distributed RL framework for solving the SoulsGym environments

Gymnasium extension for DarkSouls III, Elden Ring, and other Souls games

This is an AI agent for Street Fighter II Champion Edition.

Notes for Berkeley CS 285 Deep RL course

Democratization of RT-2 "RT-2: New model translates vision and language into action"

Reinforcement Learning for Elden Ring on Windows11

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…

This project is for a Youtube Tutorial

Full-stack TypeScript App with React, Nodejs and MongoDB