深度强化学习 (Deep Reinforcement Learning)

任课老师: 王志,陈春林

课程信息: 星期一下午2-5点, 逸夫馆3-103, 南大鼓楼校区


Announcements

  • Oct. 11th, 2021
  • Oct. 11th, 2021
  • Sept. 27th, 2021
  • Deadline for Homework 1: Nov. 15th, 2021
  • Final project paper list
  • Teaching assistant ( Email: mg20150005@smail.nju.edu.cn )

  • Lecture Slides

  • Sept. 27th, 2021
  • Oct. 11th, 2021
  • Oct. 18th, 2021
  • Oct. 25th, 2021
  • Nov. 1st, 2021
  • Nov. 8th, 2021
  • Nov. 15th, 2021
  • Nov. 22nd, 2021
  • Nov. 29th, 2021
  • Dec. 6th, 2021
  • Dec. 13rd, 2021
  • Dec. 20th, 2021
  • Dec. 27th, 2021
  • Jan. 3rd, 2022
  • Oct. 10th, 2022
  • Lecture 1: Introduction to Reinforcement Learning    [Supplementary Material]
  • Lecture 2: Preliminaries of Machine Learning
  • Lecture 3: Dynamic Programming
  • Lecture 4: Monte Carlo Methods and Temporal-Difference Learning
  • Lecture 5: Introduction to Deep Reinforcement Learning
  • Lecture 6: Policy Gradients
  • Lecture 7: Advanced Policy Gradients
  • Lecture 8: Actor-Critic Algorithms
  • Lecture 9: Value Function Methods
  • Lecture 10: Deep Q-learning
  • Lecture 11: Model-Based Reinforcement Learning
  • Lecture 12: Some Advanced Research Topics
  • Lecture 13: Presentation - Part I
  • Lecture 14: Presentation - Part II
  • Lecture 15: Presentation - Part III
  • Slides are adapted from:

  • Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, 2nd Edition
  • Sergey Levine, CS285 at UC Berkeley, Deep Reinforcement Learning