d323: CS 294: Berkeley Deep Reinforcement Learning course 2017

Berkeley Deep Reinforcement Learning course 2017

Instructors: Sergey Levine, John Schulman, Chelsea Finn

• Lecture 1: intro, derivative free optimization
• Lecture 2: score function gradient estimation and policy gradients
• Lecture 3: actor critic methods
• Lecture 4: trust region and natural gradient methods, open problems

John Schulman 1: Deep Reinforcement Learning:

John Schulman 2: Deep Reinforcement Learning:

John Schulman 3: Deep Reinforcement Learning:

John Schulman 4: Deep Reinforcement Learning:

Related Materials

Courses

• Dave Silver’s course on reinforcement learning / Lecture Videos
• Nando de Freitas’ course on machine learning
• Andrej Karpathy’s course on neural networks

Relavent Textbooks

• Sutton & Barto, Reinforcement Learning: An Introduction
• Szepesvari, Algorithms for Reinforcement Learning
• Bertsekas, Dynamic Programming and Optimal Control, Vols I and II
• Puterman, Markov Decision Processes: Discrete Stochastic Dynamic Programming
• Powell, Approximate Dynamic Programming

Source: http://rll.berkeley.edu/deeprlcourse/
Discussion: https://news.ycombinator.com/item?id=13306362