berkeley who has a deep reinforcement learning course

Prerequisites

CS189 or equivalent is a prerequisite for the course. This course will assume some familiarity with reinforcement learning, numerical optimization, and machine learning. For introductory material on RL and MDPs, see the CS188 EdX course, starting with Markov Decision Processes I, as well as Chapters 3 and 4 of Sutton & Barto.

Technology

Piazza will be used for announcements, general questions and discussions, clarifications about assignments, student questions to each other, and so on. If you are a UC Berkeley student enrolled in the course, and haven't already been added to Piazza, please email Kevin.

Late Policy

All assignments must be turned in via Gradescope on time. We will allow a total of five late days cumulatively. We will not make any additional allowances for late assignments: the late days are intended to provide for exceptional circumstances, and students should avoid using them unless absolutely necessary.

Lecture Videos

Lectures, Readings, and Assignments

Prerequisites

Related Materials

• John's lecture series at MLSS
  1. Lecture 1: intro, derivative free optimization 2. Lecture 2: score function gradient estimation and policy gradients 3. Lecture 3: actor critic methods 4. Lecture 4: trust region and natural gradient methods, open problems
• Courses
  1. Dave Silver’s course on reinforcement learning / Lecture Videos 2. Nando de Freitas’ course on machine learning 3. Andrej Karpathy’s course on neural networks

See more on rll.berkeley.edu