Back to www.rishikdhar.com | See Questions/Comments

Reinforcement Learning

Lectures By David Silver

This tutorial is a great starting place for Reinforcement Learning enthusiasts who are looking to start working in this field. Even practitioners can find several useful tips in this course material. I have only compiled these resources freely available on the internet into a coherent tutorial page, where people can collaborte with each other. Hope you find it helpful.

This course is structured in two equal halves, Conceptual and Practical RL. First five lectures drive the basic Conceptual framework using examples, illustrations and intuition.

Concepts

This first sub-section covers the theoretical portion of RL, the mechanics with a good mix of math and intuition.

Lecture 1: Introduction to RL

See Questions/Comments

Lecture 2: Markov Decision Process


See Questions/Comments

Lecture 3: Planning By Dynamic Programming


See Questions/Comments

Lecture 4: Model-Free Prediction


See Questions/Comments

Lecture 5: Model-Free Control


See Questions/Comments

In Practice

This second sub-section takes the concepts and starts building practical implementation constructs on top. Special treatment is given to the nuances in implementing RL correctly.

Lecture 6: Value Function Approximation


See Questions/Comments

Lecture 7: Policy Gradient


See Questions/Comments

Lecture 8: Integrating Learning and Planning


See Questions/Comments

Lecture 9: Exploration and Exploitation


See Questions/Comments

Lecture 10: Classic Games


See Questions/Comments

Questions and Comments