Skip to content
View siddhartha-yz's full-sized avatar
🎯
Focusing
🎯
Focusing
15 followers · 9 following
  • Nanjing

Achievements

Achievement: Pull Sharkx2

Achievements

Achievement: Pull Sharkx2

Block or report siddhartha-yz

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
siddhartha-yz/README.md

stickman-rl-lab

A reproducible 2D RL lab: an articulated stickman learns to reach a target with PPO. Independent full-course evaluation: 54/80 successes (67.5%). Does not claim upright walking.

ai-anomaly-bureau

A browser game that teaches supervised-learning intuition to first-year students, from a cat classified as bread through overfitting, hidden tests, and controlled experiments. Live demo.

dsh-mcp-gateway

Connects ChatGPT Web to a local DSH runtime over OAuth and MCP, so existing tools, skills, and policies can be called in chat without wrapping each extension.

Python · PyTorch · Git · Docker · Linux

Public study notes: learning-notes (reading notes and exercises, not a project).

zhi.yang@smail.nju.edu.cn

Pinned Loading

  1. dsh-mcp-gateway dsh-mcp-gateway Public

    Connect ChatGPT Web to a local DSH runtime over OAuth + MCP

    Python 3

  2. learning-notes learning-notes Public

    Public study notes on machine learning and deep learning (not a finished project)

    Python

  3. points-still-moving points-still-moving Public

    Python

  4. ai-anomaly-bureau ai-anomaly-bureau Public

    Browser game that teaches supervised learning to first-year students

    TypeScript 2

  5. stickman-rl-lab stickman-rl-lab Public

    A reproducible 2D reinforcement learning physics lab with a live training UI, articulated stickman control, PPO training, obstacle curricula, checkpoints, and experiment visualization.

    Python 1

  6. nju-class nju-class Public

    南京大学（NJU）个人课程笔记与复习资料：数学分析、高等代数、离散数学、程序设计等。

    Shell