Course Preview

Deep Reinforcement Learning
Instructor: Pieter Abbeel
Department: The Simons Institute for the Theory of Computing
Institution: University of California Berkeley
Platform: Independent
Price: Free
This 1-hour tutorial covers the basic of Deep Reinforcement Learning and open questions in the field. It will cover four parts: 1. Classical reinforcement learning: policy gradients, Actor-Critic, Q-learning, 2. Representation in exploration, 3. Different Approaches / Architectures: value iteration networks, prediction, modular networks, Option-Critic, feudal networks, and 4. Meta learning: MAML, RL2. This tutorial has a video lecture.