MIT: Deep Reinforcement Learning

Overview

This course on Deep Reinforcement Learning aims to teach students the key concepts and algorithms in the field. By the end of the course, learners will be able to understand and define the Q-function, explore Deep Reinforcement Learning algorithms, and delve into Policy Gradient methods. The course employs a lecture-based teaching method and is intended for individuals interested in gaining a comprehensive understanding of Deep Reinforcement Learning.

Syllabus

Intro
Classes of Learning Problems
Reinforcement Learning (RL): Key Concepts
Defining the Q-function
How to take actions given a Q-function?
Deep Reinforcement Learning Algorithms
Digging deeper into the Q-function
Downsides of Q-learning
Policy Gradient (PG): Key Idea
Policy Gradient (PG): Training
The Game of Go
AlphaGo Beats Top Human Player at Go (2016)
AlphaZero: RL from Self-Play (2018)