Xihuai Wang

A2PO-ICLR2023. Codebase for [Order Matters: Agent-by-agent Policy Optimization](https://openreview.net/forum?id=Q-neeWNVv1)

arxiv-sanity-x. Python

Scraping. Python

claude-code-mcp. Make Claude Code serve as a MCP server with minimal tools.

awesome-RL-generalization. A list of papers regarding generalization in (deep) reinforcement learning

MARL-Comm. Basic MARL algorithms with Communication

gpu-burn-utl-control. Multi-GPU CUDA stress test with Utilization Control

AlphaZero-for-Othello. (Re)-Implementation of alphazero for othello using pytorch

Common-Cooperative-Multi-Agent-Environments. Commonly-used Cooperative Multi-agent Environments Installation, Convenient Wrappers, and VectorEnv Implementation with PettingZoo (and Gymnasium) Compatibility.

opencode-quota-sidebar. TypeScript

Operating-System-Project. Project for Operating System Course, Semester 2018 Spring.

RL-Proofs. Some fundamental proofs in Reinforcement Learning.

agentic-metric. Local-only usage monitor for Claude Code and Codex CLI sessions. Live TUI dashboard, per-agent and per-model cost reports, and heatmaps — nothing leaves your machine.

SMAC-PettingZoo. Python

GFootball-Gymnasium-Pettingzoo. Google Research Football with gymnasium support.

xihuai18.github.io. SCSS

codex-mcp. TypeScript

Virtual-Routing. Simulating self-organized routing & centralized routing

sglang. SGLang is a fast serving framework for large language models and vision language models.

Reinforcement-Learning-Notes. Reinforcement Learning Notes for Reinforcement Learning: An Introduction (2nd Edition) and David Silver's Reinforcement Learning Course in UCL

pysc2. StarCraft II Learning Environment

Computer-Organization-And-Design-Review.

MaMuJoCo-PettingZoo. MaMuJoCo from https://github.com/Farama-Foundation/Gymnasium-Robotics with Convenient Wrappers and Utilities.

Go-Distributed-Storage-Service. A distributed storage service developed by Golang.

Image-Processing-in-CUDA. Implementation of Image Processing Method

RadixSort-Cuda. RadixSort using CUDA

data-structure. C++

CPU-single-cycle. JavaScript

Stream-multiprocessor-design. Verilog

Multi-cycle-CPU. Verilog

opencode-notify-native. TypeScript