Q-Learning - Model Free Reinforcement Learning and Temporal Difference Learning

Q-Learning - Model Free Reinforcement Learning and Temporal Difference Learning

Explore Q-learning, a popular model-free reinforcement learning method and type of temporal difference learning. Delve into other TD algorithms like SARSA and their connections to biological learning through dopamine. Understand Q-learning's role as a common framework for deep reinforcement learning. Learn about Monte Carlo learning, off-policy methods, and their applications. Part of a comprehensive series on reinforcement learning, this lecture follows Chapter 11 from the 2nd edition of "Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control" by Brunton and Kutz.