Reinforcement Learning

Overview

Explore the intersection of machine learning and control theory in this comprehensive video series on reinforcement learning. Delve into various methods, including model-based approaches like policy iteration, value iteration, and dynamic programming. Learn about model-free techniques such as Q-learning and temporal difference learning. Discover the principles of nonlinear control through Hamilton Jacobi Bellman equations and dynamic programming. Investigate deep reinforcement learning, focusing on neural networks for learning control laws and their applications in fluid dynamics and control. Gain a thorough understanding of both traditional and cutting-edge reinforcement learning techniques over the course of 3 hours and 30 minutes.

Syllabus

Reinforcement Learning: Machine Learning Meets Control Theory.
Reinforcement Learning Series: Overview of Methods.
Model Based Reinforcement Learning: Policy Iteration, Value Iteration, and Dynamic Programming.
Q-Learning: Model Free Reinforcement Learning and Temporal Difference Learning.
Nonlinear Control: Hamilton Jacobi Bellman (HJB) and Dynamic Programming.
Deep Reinforcement Learning: Neural Networks for Learning Control Laws.
Overview of Deep Reinforcement Learning Methods.
Deep Reinforcement Learning for Fluid Dynamics and Control.