CS 285 at UC Berkeley

Deep Reinforcement Learning

Lectures: Mon/Wed 5-6:30 p.m., Li Ka Shing 245

IMPORTANT: If you are an undergraduate or 5th year MS student, or a non-EECS graduate student, please fill out this form to apply for enrollment into the Fall 2022 version of the course. Do not email the course instructors about enrollment -- all students who fill out the form will be reviewed. We will enroll off of this form during the first week of class. We will not be using the official CalCentral wait list, just this form.

Lecture recordings from the current (Fall 2022) offering of the course: watch here

Looking for deep RL course materials from past years?

Recordings of lectures from Fall 2021 are here, and materials from previous offerings are here.

Email all staff (preferred): cs285-staff-f2022@lists.berkeley.edu
  • Instructor Sergey Levine


    Office Hours: After lecture

  • Head GSI Marwa Abdulhai


    Office Hours: Tuesday 3-4pm (BWW 1206)

  • GSI Homer Walke


    Office Hours: Monday 11am-12pm (BWW 1206)

  • GSI Yuqing Du


    Office Hours: Wednesday 10:30-11:30am (BWW 1206)

  • uGSI Zheyuan Hu


    Office Hours: Thursday 3:30-4:30pm (BWW 1206)

  • uGSI Anikait Singh


    Office Hours: Friday 5-6pm (BWW 1206)

Week 1 Overview

Course Introduction

Week 2 Overview

Imitation Learning

Week 3 Overview

Intro to RL and Policy Gradients

Week 4 Overview

Actor Critic and Value Function Methods

Week 5 Overview

Value Functions and Q-learning

Week 6 Overview

Advanced Policy Gradients and Model-based learning

Week 7 Overview

Advanced Model Learning and Imitating Optimal Controllers

Week 10 Overview

RL Algorithm Design and Variational Inference

Week 11 Overview

Control as Inference and Inverse Reinforcement Learning

Week 12 Overview

Meta-Learning and Transfer Learning

Week 13 Overview

Challenges and Open Problems