UC Berkeley CS 285: Deep Reinforcement Learning →0/11

CS 285: Lecture 1, Introduction. Part 2

CS 285: Lecture 1, Introduction. Part 3

CS 285: Lecture 2, Imitation Learning. Part 1

CS 285: Lecture 2, Imitation Learning. Part 2

CS 285: Lecture 2, Imitation Learning. Part 3

CS 285: Lecture 4, Part 1

Lecture 5, Part 1 (CS 285)

Lecture 5, Part 3 (CS 285)

Lecture 5, Part 4 (CS 285)

Lecture 6, Part 1 (CS 285)

Lecture 6, Part 2 (CS 285)

Lecture 6, Part 1 (CS 285)

Sergey Levine UC Berkeley

Professor

25:13·2020·graduate level

This lecture introduces advanced policy gradient concepts, focusing on the connection between policy gradients and the Fisher information matrix in natural policy gradients.

AI & ML Reinforcement Learning Policy Gradient Fisher Information Matrix Trust Region Methods

Previous · Lecture 9

Lecture 5, Part 4 (CS 285)

Next · Lecture 11

Lecture 6, Part 2 (CS 285)

Seminar notes & discussion

Sign in to comment

No public seminar notes on this lecture yet.

Part of course11 lectures

CS 285: Deep Reinforcement Learning

Prof. Sergey Levine

Imitation learning, policy gradients, actor-critic algorithms, value-function Q-learning, model-based RL, offline reinforcement learning, exploration, and inverse RL.

View full syllabus →

Related lectures

Lecture 6, Part 2 (CS 285)

Sergey Levine · UC Berkeley

Next in CS 285 · Lecture 11

Lecture 5, Part 1 (CS 285)

Sergey Levine · UC Berkeley

Shared subfield · Reinforcement Learning & Policy Gradient

Lecture 5, Part 3 (CS 285)

Sergey Levine · UC Berkeley

Shared subfield · Reinforcement Learning & Policy Gradient

Lecture 5, Part 4 (CS 285)

Sergey Levine · UC Berkeley

Shared subfield · Reinforcement Learning

RL Course by David Silver - Lecture 7: Policy Gradient Methods

David Silver · Google DeepMind

Shared subfield · Reinforcement Learning

HydroGym: A Reinforcement Learning Platform for Fluid Dynamics

Steven L. Brunton · University of Washington

Shared subfield · Reinforcement Learning