Mathematical Foundation of Reinforcement Learning
Published:
UMich EECS 498-007 / 598-005: Deep Learning for Computer Vision
Course Website
Course Overview
I take this course together with the David Silver’s “Reinforcement Learning” course on Coursera to deepen my understanding of reinforcement learning. This course focuses on the mathematical foundations underlying reinforcement learning techniques.
However, the organization of some chapters in this course differs from that of David Silver’s and this course lacks some important topics of the RL. But I still find it a good complement to David Silver’s course.
My Learning Journey
- 2026.1.29 L1-Basic concepts
- 2026.1.29 L2-Bellman equation
- 2026.1.31 L3-Bellman optimality equation
- 2026.2.4 L4-Value iteration and policy iteration
- 2026.2.4 L5-Monte Carlo methods
- 2026.2.5 L6-Stochastic approximation
- 2026.2.6 L7-Temporal-Difference Learning
- 2026.2.7 L8-Value function methods
- 2026.2.8 L9-Policy gradient methods
- 2026.2.9 L10-Actor Critic