Explore the powerful technique of reinforcement learning in this 26-minute video lecture by Steve Brunton. Gain a high-level overview of this field at the intersection of machine learning and control theory, inspired by biological systems' learning processes. Delve into the mathematics behind reinforcement learning, understand Markov Decision Processes, and tackle the credit assignment problem. Discover various optimization techniques and examine real-world applications of reinforcement learning. Learn about Q-Learning and Hindsight Replay as key algorithms in the field. Perfect for those interested in machine learning, control theory, and their practical applications in solving complex problems.
Overview
Syllabus
Introduction.
Reinforcement Learning Overview.
Mathematics of Reinforcement Learning.
Markov Decision Process.
Credit Assignment Problem.
Optimization Techniques for RL.
Examples of Reinforcement Learning.
Q-Learning.
Hindsight Replay.
Taught by
Steve Brunton
