Reinforcement Learning: From Theory to Algorithm (CS7309)

---

Time and Venue :

-   Time : 14:55 - 17:40 , Thursday , Week 1 - 16

-   Venue : Chenruiqiu Building 310

Instructor :

-   Prof : Junni Zou

-   Email : zoujunni@sjtu.edu.cn

-   Office : 3-437, SEIEE Building

Teaching Assistant :

-   Teaching Assistant : Tianchi Zhang

-   Email : zhangtianshi@sjtu.edu.cn

Reference Book :

-   Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, Second Edition, 2018

Grading Policy :

-   Presentation: 30%

-   Final Project: 70%

Lecture Slides :

We use the lecture slides of Prof. David Silver as a reference: David Silver
-   Lecture 1: Introduction
-   Lecture 2: Markov Decision Processes
-   Lecture 3: Dynamic Programming
-   Lecture 4: Model-Free Prediction (1)
-   Lecture 5: Model-Free Prediction (2)
-   Lecture 6: Model-Free Control
-   Lecture 7: Value Function Approximation
-   Lecture 8: Advanced DQN
-   Lecture 9: Policy Gradient
-   Lecture 10: A3C & PPO
-   Lecture 11: DDPG & Soft AC
-   Lecture 12: Optimal Control and Planning
-   Lecture 13: Model-Based Reinforcement Learning
-   Lecture 14: Variational Inference
-   Lecture 15: Meta-Reinforcement Learning

Lecture Slides :

-   Requirements for Final Project

 

Reinforcement Learning (CS489)

---

Time and Venue :

-   Time : 10:00 - 11:40 , Friday , Week 1 - 16

-   Venue : East Zhongyuan 3-103

Instructor :

-   Prof : Junni Zou

-   Email : zoujunni@sjtu.edu.cn

-   Office : 3-437, SEIEE Building

Teaching Assistant :

-   Teaching Assistant : Yuankun Jiang

-   Email : yuankunjiang@sjtu.edu.cn

Reference Book :

-   Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, Second Edition

Grading Policy :

-   Homework and Project: 50%

-   Final Exam : 50%

Lecture Slides :

We use the lecture slides of Prof. David Silver as a reference: David Silver
-   Lecture 0: Experiments Setup
-   Lecture 1: Introduction and Course Overview
-   Lecture 2: Markov Decision Processes
-   Lecture 3: Dynamic Programming
-   Lecture 4: Model-Free Prediction (1)
-   Lecture 5: Model-Free Prediction (2)
-   Lecture 6: Model-Free Control
-   Lecture 7: Value Function Approximation
-   Lecture 8: Convolutional Neural Network
-   Lecture 9: DQN Variants
-   Lecture 10: Policy Gradient
-   Lecture 11: Integrating Learning

Assignments :

-   Assignment 1: Dynamic Programming
-   Assignment 2: Model-Free Prediction
-   Assignment 3: Model-Free Control
-   Assignment 4: Value Function Approximation
-   Assignment 5: Policy Gradient

 

Discrete Mathematics (MA115)

---

Time and Venue :

-   Time : 14:00 - 15:40 , Friday , Week 1 - 16

-   Venue : East Shangyuan 509

Instructor :

-   Prof : Junni Zou

-   Email : zoujunni@sjtu.edu.cn

-   Office : 3-437, SEIEE Building

Teaching Assistant :

-   Teaching Assistant : Qiaoyu Lu

-   Email : luqiaoyu@sjtu.edu.cn

Reference Book :

-   Kenneth H.Rosen, Discrete Mathematics and Its Applications, Seventh Edition

-   Logic : Chapter 1
             Chapter 2
             Chapter 3
             Chapter 4
             Chapter 5

-   Graph : Ch1
               Ch2

Grading Policy :

-   Attendence and Homework : 30%

-   Final Exam : 70%