Code

  • RL Theory in Lean
    Here I take the ambitious goal to formalize RL theory in Lean. I have formalized the almost sure convergence of linear TD and Q learning with Markovian samples.

  • Reinforcement Learning: An Introduction
    This repo is a Python implementation of the RL textbook from Sutton & Barto. This is my course project when I took Rich’s RL course in my first term at the University of Alberta, when the book was about to complete.

  • PyTorch Deep RL
    This repo includes almost all codes of my papers during my DPhil. It helps me prototype new ideas easily but is unfortunately no longer maintained.

Blog

Hobby

Current UVA Students

  • If you need me to approve your OPT / CPT (because I am listed as your advisor), please email me the required information. You can find the required information here.