Skip to content
View Infinity-Todd's full-sized avatar
2 followers · 4 following
  • UCSD
  • USA
  • 15:14 (UTC -12:00)

Block or report Infinity-Todd

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
Infinity-Todd/README.md

😎 Todd Zhu | Infinity-Todd

Python PyTorch NumPy Pandas Gymnasium VS Code PyCharm

🚀 About Me | 关于我

  • 👋 Hi! I'm Todd Zhu, a 20 y.o. 🐍 Pythonista & Data Scientist
  • 📍 Based in Ningbo/China
  • 🧠 Currently diving into: Reinforcement Learning, Deep Learning, Robotics
  • 🛠️ 常用工具/Skills: Python, NumPy, Pandas, PyTorch, Gymnasium, PyCharm
  • 🔭 开放合作/Collab: Always happy to connect & work on open source!

🏆 Main Projects | 项目精选

  • 🐍 Snake RL Project
    A customizable Snake reinforcement learning environment with reward shaping, observation design, vectorized training, and TensorBoard logging (Gymnasium + Stable-Baselines3).

  • 🤖 Footstep-Guided Humanoid Obstacle Avoidance
    Footstep-guided slalom locomotion for the JRVC-1 humanoid in MuJoCo with a custom PyTorch controller for stable, collision-free walking; Apple Silicon MPS supported.

💡 Skills | 技能清单

🚩 Language 💻 Libraries/Tools 🧩 Areas
Python 🐍 NumPy, Pandas, PyTorch, Gymnasium, Matplotlib Data Science, RL, ML, Visualization
Markdown ✍️ VS Code, PyCharm, Git Documentation, Collaboration
English 🇺🇸 Technical communication in English

🛸 Fun Facts | 彩蛋

  • 🚴‍♂️ Love soccer, sci-fi, modeling, and robotics!
  • 💬 I can help you with RL environments, data cleaning, and visualization

📫 Contact | 联系我

👋 欢迎关注 / Let's Connect!   |   ⭐️ Star my repos if you like!

Popular repositories Loading

  1. Footstep-Guided-Humanoid-Obstacle-Avoidance Footstep-Guided-Humanoid-Obstacle-Avoidance Public

    Footstep-guided slalom locomotion for a JRVC-1 humanoid in MuJoCo, trained with a custom PyTorch policy to track discrete step targets and avoid obstacles.

    Python 6 1

  2. Infinity-Todd Infinity-Todd Public

    Config files for my GitHub profile.

    2

  3. Snake-RL Snake-RL Public

    A reinforcement learning project that trains an agent to play the classic Snake game using Proximal Policy Optimization (PPO) from Stable-Baselines3.

    Python 2