Model Based Reinforcement Learning - Policy Iteration, Value Iteration, and Dynamic Programming

Model Based Reinforcement Learning - Policy Iteration, Value Iteration, and Dynamic Programming

Explore dynamic programming as a fundamental concept in model-based reinforcement learning. Delve into policy iteration and value iteration techniques, leading to an understanding of the quality function and Q-learning. Learn how these methods form the basis for solving reinforcement learning problems. Gain insights from examples and explanations provided in this 27-minute lecture, which is part of a comprehensive series on reinforcement learning based on the new Chapter 11 from the 2nd edition of "Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control" by Brunton and Kutz.