Room no. 308

The room of our random experiments

View My GitHub Profile

RL Math

by Chaitanya

These notes are based on Mathematical Foundations of Reinforcement Learning by Shiyu Zhao.


Prerequisites: Basic Concepts in RL: Markov Decision Processes, State, Action, Reward, Policy, Transition Probability, \(\gamma\), Trajectory, Return. Episodes.

  1. Chapter 2: State Values and Bellman Equation
  2. Chapter 3: Optimal State Values and Bellman Optimality Equation
  3. Chapter 4: Value Iteration and Policy Iteration
  4. Chapter 5: Monte Carlo Methods