Deep Reinforcement Learning

Information

• Instructor: Zhi Wang, Chunlin Chen

• Time: 14:00-17:00pm, Monday

• Location: 516 Xiexin Building, School of Management and Engineering, Nanjing University at Gulou Campus

Announcements

• Feb. 26th, 2024   |   For final project presentation: paper list

• Feb. 26th, 2024   |   Teaching Assitant: Zican Hu (Email: huzican0419@gmail.com)

Lecture Slides

• 2024.02.26   |   Lecture 1: Introduction to Reinforcement Learning

• 2024.03.04   |   Lecture 2: Preliminaries of Machine Learning

• 2024.03.11   |   Lecture 3: Dynamic Programming

• 2024.03.18   |   Lecture 4: Monte-Carlo Methods and Temporal-Difference Learning

• 2024.03.25   |   Lecture 5: Introduction to Deep Reinforcement Learning

• 2024.04.01   |   Lecture 6: Policy Gradient

• 2024.04.08   |   Lecture 7: Advanced Policy Gradient

• 2024.04.15   |   Lecture 8: Actor-Critic Algorithms

• 2024.04.22   |   Lecture 9: Value Function Methods

• 2024.04.29   |   Lecture 10: Deep Q-learning

• 2024.05.06   |   Lecture 11: Offline Reinforcement Learning

• 2024.05.13   |   Lecture 12: Multi-Task and Meta Reinforcement Learning

• 2024.05.20   |   Lecture 13: Multi-Agent Reinforcement Learning

• 2024.05.27   |   Lecture 14: Presentation - Part I

• 2023.06.03   |   Lecture 15: Presentation - Part II

• 2023.06.10   |   Class Suspension (Dragon Boat Festival)

Note: References for lecture slides

• Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, 2nd Edition

• Sergey Levine, CS285 at UC Berkeley, Deep Reinforcement Learning