1
Deep Reinforcement Learning (Spring 2017, UC Berkeley). Instructors: Sergey Levine, John Schulman, and Chelsea Finn.
FREE
This course includes
Hours of videos
694 years, 4 months
Units & Quizzes
25
Unlimited Lifetime access
Access on mobile app
Certificate of Completion
This course will assume some familiarity with reinforcement learning, numerical optimization and machine learning. The course covers topics: Supervised learning and decision making; Basic reinforcement learning: Q-learning and policy gradients; Advanced model learning and prediction; Advanced deep reinforcement learning: trust region policy gradients, actor-critic methods, exploration; Open problems and research talks.
Course Currilcum
- Lecture 01 – Introduction Unlimited
- Lecture 02 – Supervised Learning of Behaviors: Deep Learning, Dynamical Systems, and Behavior Cloning Unlimited
- Lecture 03 – Optimal Control, Trajectory, Optimization, and Planning Unlimited
- Lecture 04 – Learning Dynamical System Models from Data Unlimited
- Lecture 05 – Learning Policies by Imitating Optimal Control Unlimited
- Lecture 06 – Direct Collocation Methods for Trajectory Optimization and Policy Learning Unlimited
- Lecture 07 – Markov Decision Processes and Solving Finite Problems Unlimited
- Lecture 08 – Policy Gradient Methods Unlimited
- Lecture 09 – Q-Function Learning Methods Unlimited
- Lecture 10 – Advanced Q-Function Learning Methods Unlimited
- Lecture 11 – Advanced Model Learning Unlimited
- Lecture 12 – Advanced Topics in Imitation Learning and Safety Unlimited
- Lecture 13 – Inverse Reinforcement Learning Unlimited
- Lecture 14 – Advanced Policy Gradient Methods: Natural Gradient, TRPO, and More Unlimited
- Lecture 15 – Variance Reduction for Policy Gradient Methods Unlimited
- Lecture 16 – Policy Gradient Methods: Pathwise Derivative Methods and Wrap-Up Unlimited
- Lecture 17 – The Exploration Problem Unlimited
- Lecture 18 – Asynchronous and Parallel Algorithms Unlimited
- Lecture 19 – Transfer in (Deep) Reinforcement Learning Unlimited
- Lecture 20 – Neural Architecture Search with Reinforcement Learning Unlimited
- Lecture 21 – Generalization and Safety in Reinforcement Learning and Control Unlimited
- Lecture 22 – Deep Reinforcement Learning with Forward Prediction, Memory, and Hierarchy Unlimited
- Lecture 23 – Towards a Unified View of Supervised Learning and Reinforcement Learning Unlimited
- Lecture 24 – Adversarial Examples in Reinforcement Learning Unlimited
- Lecture 25 – Review Unlimited
