CS 185/285 at UC Berkeley
Deep Reinforcement Learning
Lectures: 9 - 10 am on Wednesdays and 8 - 10 am on Fridays, both in Hearst Annex A1
Announcement: Homework 5 (Offline RL) is now released.
Announcement: The default final project options are now available: Offline-to-Online RL Default Final Project and LLM RL Default Final Project.
Announcement: Homework 4 (LLM RL) is now released.
Announcement: The final project outline has been released.
Looking for deep RL course materials from past years?
Recordings of lectures from Fall 2023 are here, and materials from previous offerings are here.Email all staff (preferred): cs285-staff-sp2026@lists.eecs.berkeley.edu
-
Instructor Sergey Levine
svlevine@eecs.berkeley.edu
Office Hours: Wednesdays 8 - 9 AM in Hearst Annex A1
-
-
-
-
-
GSI Mitsuhiko Nakamoto
nakamoto@eecs.berkeley.edu
Office Hours: Thursday 4p-5p Berkeley Way West 1204
-
GSI Catherine Glossop
catherine_glossop@berkeley.edu
Office Hours: Thu 10a-11a in Berkeley Way West 1211
Week 1 Overview
Course Intro & Imitation Learning
Week 2 Overview
Imitation Learning & RL Basics
Week 3 Overview
Policy Gradients & Actor Critic
Week 5 Overview
Advanced Policy Gradients
Week 6 Overview
Variational Inference
Week 7 Overview
Finishing VI & LLM RL
Week 9 Overview
Offline Reinforcement Learning
Final Project Information
Default Project Options
Project Outline
Homeworks
See Syllabus for more information (including rough schedule).
Lecture Slides
See Syllabus for more information.
- Lecture 1: Introduction
- Lecture 2: Behavioral Cloning
- Lecture 3: Behavioral Cloning Part 2
- Lecture 4: RL Basics
- Lecture 5: Policy Gradients
- Lecture 6: Actor Critic
- Lecture 7: Value-Based RL
- Lecture 8: Q-learning in Practice
- Lecture 9: Advanced Policy Gradients Part 1
- Lecture 10: Advanced Policy Gradients Part 2
- Lecture 11: Variational Inference
- Lecture 12: VI in RL
- Lecture 13: Control as Inference
- Lecture 14: LLM RL
- Lecture 15: Model-Based RL Part 1
- Lecture 16: Model-Based RL Part 2
- Lecture 17: Offline RL Part 1
- Lecture 18: Offline RL Part 2
- Lecture 19: TBD
- Lecture 20: TBD
- Lecture 21: TBD
- Lecture 22: TBD
- Lecture 23: TBD
Discussion Section Slides
See Syllabus for more information.
- Section 1: PyTorch Tutorial
- Section 2 Part 1: Probability Review
- Section 2 Part 2: BC Distributional Shift
- Section 3: Policy Gradients and Actor Critic
- Section 4: DQN and SAC
- Section 5: Advanced Policy Gradients
- Section 6: Variational Inference
- Section 7: IRL and LLM RL
- Section 8: Model-Based RL
- Section 9: TBD
- Section 10: TBD
- Section 11: TBD
- Section 12: TBD