This is the Math You Need to Master Reinforcement Learning
Unapologetically diving into the mathematics of reinforcement learning. We explore the policy gradient theorem and policy gradient methods.
Icon by Freepik
https://www.freepik.com/icon/light-bu...
0:00 The Simple Example
3:14 Causal Dependency Graph
7:42 What is a Policy?
10:32 Motivation of Policy Gradient Methods
15:58 The Full Math
28:04 Summary
