Tianyang Wu

KataCR. A non-embedded AI for Clash Royale based on RL and CV.

go2_rl_gym. This is a repository for reinforcement learning implementation based on Unitree Go2. Official implementation of RSS 2026.

kaiwu_taichu. 腾讯开悟智能体比赛（王者荣耀AI赛道，四足机械狗赛道，稳定版）

RoboGauge. Evaluate the performance metrics for different RL locomotion models.

Clash-Royale-Detection-Dataset. Build a generation object detection dataset for Clash-Royale

unitree_cpp_deploy. Unitree Robot with cpp deploy from unitree_rl_lab

LaTex-Projects. 保存latex模板和各种作业及报告

Clash-Royale-Replay-Dataset. Replays for training offline-rl policy.

arduino_pid_controlled_motor. Arduino + L298N + Motor & Encoder = Speed Closed-Loop Control

humanoid-gym. Reinforcement Learning for Humanoid Robot

humanoid_rl_gym. Humanoid Robot + IsaacGym + RL + Evaluation + Deployment

KataCV. 用JAX对计算机视觉(CV)中的经典深度神经网络、目标识别、OCR，自然语言处理(NLP)中的经典模型进行复现

Decision-Transformer-JAX. Implemented Decision Transformer in Atari environment using JAX

Blog-SourceCode. wty-yy.github.io - Source code

wty-yy.github.io. My Hexo blog

tri-fingers. 三指机器人+强化学习控制

quickdraw-online. 大三暑期实习大作业，对google开源数据集quickdraw进行筛选后，实现一个在线网页版本的“你画我猜”实时识别功能。（对原仓库优化布局）

trifinger-gym. based on leibnizgym

Clash-Royale-Dataset. 1. Object detection 2. Classificiation 3. OCR

skills. The skills I use for agents.

arduino_wheel_drive. A simple ROS2 Humble Control Hardware Interface for differential drive control of robot whose motors are connected via an Arduino (or similar microcontroller). Fork from: https://github.com/joshnewans/diffdrive_arduino

XJTU-CVPR-2024. XJTU 2024年CVPR研究生课程

trifinger-gym-train. Training trifinger gym

isaac-sim-use-cases. Some use cases documented in leanring isaac-sim

TSP. New algorithm for solving TSP

KataRL. KataRL is a reinforcement learning model framework.

DeepLearing-Summer. 大二下暑期，基于TensorFlow2学习基础神经网络模型