张恒溪|ZHANG Hengxi

张恒溪|ZHANG Hengxi

Tsinghua University

Teaching

Theoretical Course

Mathematics in Reinforcement learning

Theoretical Course, Bilibili, 2025

This theoretical series is designed to walk you through the mathematical foundations that are central to modern RL algorithms. Throughout the course, we will cover key topics including unbiased versus biased estimations, the structure of Markov Decision Processes (MDPs), the mathematical definition and role of policies, value functions, and essential methods such as Monte Carlo sampling. Just come over and have fun

Programming Course

From 0 to 1: Code the Classic Reinforcement Learning Algorithms

Programming Course, Bilibili, 2025

This coding series is designed to lead you from basic to advanced reinforcement learning by walking through hands-on Python implementations of the classic algorithms. Step by step, you’ll follow along as each method is explained and developed line by line, starting from the foundational Q-Learning and progressing through modern deep RL including DQN, DDPG, MADDPG, PPO, and SAC.