Reinforcement Learning - Machine Learning Meets Control Theory

Overview

This course provides a high-level overview of reinforcement learning, including leading algorithms and applications at the intersection of machine learning and control theory. The syllabus covers topics such as the mathematics of reinforcement learning, Markov Decision Process, credit assignment problem, optimization techniques for RL, and specific algorithms like Q-Learning and Hindsight Replay. The course aims to teach learners about the principles and applications of reinforcement learning, suitable for individuals interested in machine learning, control theory, and artificial intelligence. The teaching method involves a 26-minute video lecture.

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.