UC Berkeley · Levine

Berkeley CS 285 · Deep Reinforcement Learning

0 / 31 complete

Part 1 — Foundations: Imitation to Policy Gradients

01 Introduction
02 Imitation Learning
04 Introduction to RL
05 Policy Gradients
★ HW1 · Imitation Learning

Part 2 — Value-Based Methods

06 Actor-Critic Algorithms
07 Value Function Methods
08 Deep RL with Q-Functions
09 Advanced Policy Gradients
★ HW2 · Policy Gradients
★ HW3 · Q-Learning & Actor-Critic

Part 3 — Model-Based RL and Exploration

10 Optimal Control and Planning
11 Model-Based RL
12 Model-Based RL with Policies
13 Exploration I
14 Exploration II

Part 4 — Offline RL and Theory

15 Offline RL I
16 Offline RL II
17 RL Theory
★ HW4 · LLM RL
★ HW5 · Offline RL

Part 5 — RL as Inference

18 Variational Inference
19 Control as Inference
20 Inverse Reinforcement Learning

Part 6 — Frontiers

21 RL with Sequence Models & LLMs
22 Transfer Learning & Meta-Learning
23 Challenges & Open Problems

Part 7 — Guest Lectures

undefined Eric Mitchell · RLHF
undefined Andrea Zanette · Statistical Foundations of RL
undefined Aviral Kumar
undefined Dorsa Sadigh

Find it on the board

Search the course

Every lesson, definition, and problem is indexed. Try “four subspaces” or “pivot”.