View on GitHub

rlcourse

An Introduction to Reinforcement Learning

Link back to the Syllabus

All readings are from the textbook. These readings are designed to be short, so that it should be easy to keep up with the readings.

This schedule is tentative, and is likely to change throughout the semester.

Link to Schedule from Fall 2019.

Week Date Topic Deadlines
1 September 2, 4 Introduction to AI and Organizing discussions

Worksheet in class about random variables and expectations

Background on Statistics and Probability: Part 1
In preparation for Week 2, watch videos in Course 1, Module 1, starting with the K-Armed Bandit

Complete Quiz 1 by midnight on Tuesday, September 8 link

Notebook for C1M1 is due on Friday, September 11, link
2 September 7 Labor Day Holiday, no Classes Complete Practice Quiz 1 by midnight on Tuesday, September 8 link
2 September 9 Background on Statistics and Probability: Part 2

Worksheet on background
 
2 September 11 Review with Question-and-Answer session

Worksheet on C1M1
Complete Graded Notebook for Week 1 by midnight on Friday, September 11, link
3 September 14 Review, Q&A session and Worksheet on C1M2, for content Mini-Course 1, Module 2: Markov Decision Processes Sept. 15 last day to drop courses without fees.

Complete Practice Quiz by midnight on Sunday, September 13 link
3 September 16 In-class Worksheet (the slides and the Worksheet on C1M2),
Extra: this proof for the return being bounded.
Complete Peer-graded Assignment by midnight on Friday, September 18 link
3 September 18 Fun Session: Rich Sutton will come give a guest lecture! We will watch a part of a video from Rich, and he will then answer questions. The video is here, we will play part of it in class followed by live Q&A with Rich. Complete Peer-review by Monday September 21 night: Link
4 September 21 Review C1M3 and start worksheet questions for Mini-Course 1, Module 3: Value Function and Bellman Equations,
Extra: Derivation of Bellman Equation
Complete Practice Quiz 3 by midnight on Sunday, September 20 link
4 September 23 Q&A for C1M3 and start Worksheet on C1M3  
4 September 25 Worksheet on C1M3 Complete Graded Quiz by Midnight, Friday, September 25, link
5 September 28 Dynamic Programming review Oct. 2 last day to drop course (50% fees).

Complete Practice Quiz 4 by midnight on Sunday, September 27 link
5 September 30 Discussion day  
5 October 2 Worksheet for C1M4 Complete Graded Notebook for C1M4 by midnight on Friday, October 2 link
6 October 5 Review of Monte Carlo Methods In preparation for Week 6, watch videos in Mini-Course 2, Module 1. Complete Blackjack notebook by midnight on Sunday October 4.
6 October 7 The Worksheet on C2M1  
6 October 9 Fun Session: AI and Games
Link to games
Complete Graded Quiz by midnight on Thursday, October 8, link
7 October 12 Holiday Complete Practice Quiz by midnight on Sunday, October 11, link
7 Ocobter 14 Temporal Difference Learning Methods for Prediction  
7 October 16 The Worksheet on C2M2 Complete Graded Notebook by midnight on Friday, October 16, link
8 October 19 Temporal Difference Learning Methods for Control with additional note about the difference between Sarsa, Expected Sarsa and Q-learning. Finished off slido qs from last week. Complete Practice Quiz by midnight on Sunday, October 18, link
8 October 21 Continue review. Start Worksheet on C2M3.  
8 October 23 Finish worksheet Worksheet on C2M3 and any remaining questions. Complete Graded Notebook by midnight on Friday, October 23, link
9 October 26 Planning Learning and Acting review Complete Practice Quiz by midnight on Sunday, October 25, link
9 October 28 Worksheet on C2M4.  
9 October 30 Assignment and Quiz review session Complete Graded Notebook by midnight on Friday, October 30, link
10 November 2 C3M1: Prediction with Approximation review Complete Practice Quiz by midnight on Sunday, November 1
10 November 4 Discussion day  
10 November 6 Worksheet on C3M1 Complete Graded Notebook by midnight on Friday, November 6, link
11 November 9, 11, 13 No classes: Reading week Start Capstone Project. Here is the project overview.
12 November 16 Midterm Review  
12 November 18 Go over two Practice Exams  
12 November 20 Midterm on November 20. Go to the regular Zoom link. The exam is 50 minutes.  
13 November 23 Constructing Features for Prediction Complete Practice Quiz by midnight on Sunday, November 22
13 November 25 Worksheet for C3M2  
13 November 27 Worksheet for C3M2 Complete Graded Notebook by midnight on Friday, November 27
14 November 30 C3M3: Control with Approximation Review November 30 last day to withdrawal from course with W

Complete Practice Quiz by midnight on Sunday, November 29
14 December 2 Worksheet for C3M3  
14 December 4 Course Review Complete Graded Notebook by midnight on Friday, December 4

Submit Capstone Project zip file by midnight on Monday, December 7.
15 December 7 No class! Instead, we will schedule a review session closer to the exam.  
Final Friday, December 11, 2020, 2:00 - 4:00 p.m. Final Exam The final is open-book. You can use the textbook and any notes. You cannot use the internet. Everything must be downloaded and locally on your machine or physical documents.