CS285: Deep Reinforcement Learning

University: UC Berkeley

Instructor: Sergey Levine

📚 笔记目录 (Table of Contents)

Part 1: Basics

• Lec 1: Imitation Learning

• Lec 2: Introduction to Reinforcement Learning

• Lec 3: Policy Gradients

• Lec 4: Actor-Critic Algorithms

• Lec 5: Value Function Methods

• Lec 6: Deep RL with Q-Functions

• Lec 7: Advanced Policy Gradient

• Lec 8: Optimal Control and Planning

• Lec 9: Model-Based Reinforcement Learning

• Lec 10: Model-Based Policy Learning

Part 2: Advanced Topics

• Lec 11: Exploration (Part 1)

• Lec 12: Exploration (Part 2)

• Lec 13: Offline Reinforcement Learning (Part 1)

• Lec 14: Offline Reinforcement Learning (Part 2)

• Lec 15: Reinforcement Learning Theory Basics

• Lec 16: Variational Inference and Generative Models

• Lec 17: Connection between Inference and Control

• Lec 18: Inverse Reinforcement Learning

• Lec 19: RL with Sequence Models

• Lec 20: Meta-Learning and Transfer Learning

• Lec 21: Challenges and Open Problems