CS 285 at UC Berkeley
Deep Reinforcement Learning
Lectures: Mon/Wed 1011:30 a.m., Soda Hall, Room 306
Lectures will be streamed and recorded. The course is not being offered as an online course, and the videos are provided only for your personal informational and entertainment purposes. They are not part of any course requirement or degreebearing university program.
Piazza is the preferred platform to communicate with the instructors. However, if for some reason you wish to contact the course staff by email, use the following email address: cs285fall2019@googlegroups.com.
Looking for deep RL course materials from past years?
Recordings of lectures from fall 2018 are here, and materials from previous offerings are here.
Instructor Sergey Levine
svlevine@eecs.berkeley.edu
Office Hours: Wed 11.3012.30pm, Soda 347 alcove




Week 1 Overview
Course Introduction, Imitation Learning
Week 2 Overview
Imitation Learning
Week 4 Overview
Policy Gradients and Actor Critic
Week 5 Overview
Value Functions and Qlearning
Week 6 Overview
Advanced Policy Gradients and Modelbased learning
Week 7 Overview
Advanced Model Learning and Imitating Optimal Controllers
Week 8 Overview
Connection between inference and control
Week 9 Overview
Inverse Reinforcement Learning and multitask learning
Week 10 Overview
Parallelism for RL
Week 11 Overview
Exploration
Week 13 Overview
Information Theory, Challenges, Open Problems
Homeworks
See Syllabus for more information.
Lecture Slides
See Syllabus for more information.
 Lecture 1: Introduction and Course Overview
 Lecture 2: Supervised Learning of Behaviors
 Lecture 3: TensorFlow and Neural Nets Review Session (notebook)
 Lecture 4: Introduction to Reinforcement Learning
 Lecture 5: Policy Gradients
 Lecture 6: ActorCritic Algorithms
 Lecture 7: Value Function Methods
 Lecture 8: Deep RL with Qfunctions
 Lecture 9: Advanced Policy Gradients
 Lecture 10: Modelbased Planning
 Lecture 11: Modelbased Reinforcement Learning
 Lecture 12: Modelbased Policy Learning
 Lecture 13: Variational Inference and Generative Models
 Lecture 14: Control as Inference
 Lecture 15: Inverse Reinforcement Learning
 Lecture 16: Transfer and Multitask Learning
 Lecture 17: Distributed RL
 Lecture 18: Exploration (Part 1)
 Lecture 19: Exploration (Part 2)
 Lecture 20: Metalearning
 Lecture 21: Information Theory, Open Problems