Reinforcement Learning

Overview

This course covers the following topics: Reinforcement Learning methods, Model Based Reinforcement Learning, Q-Learning, Nonlinear Control, Deep Reinforcement Learning, and Deep Reinforcement Learning methods for Fluid Dynamics and Control. The course aims to teach learners about the intersection of Machine Learning and Control Theory, with a focus on using Neural Networks for learning control laws. The intended audience for this course includes individuals interested in Machine Learning, Control Theory, and applications in Fluid Dynamics. The teaching method involves a series of lectures providing an overview of methods and hands-on practice with different Reinforcement Learning techniques.

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.