Schedule

Unless noted otherwise, all readings are from Reinforcement Learning: An Introduction, 2nd Ed., Sutton and Barto

Date Topic/Notes Reading
Assignment due
9/5 Introduction to RL SB 1.1--1.6
Self Assessment (Solutions)
9/9 Bandit Problems SB 2.1--2.10
 
9/12 Bandit Problems
Intro assignment DUE (Friday)
9/16 MDPs SB 3.1--3.8
 
9/19 MDPs

Bandits assignment DUE (Friday)
9/23 Dynamic Programming SB 4.1--4.8
 
9/26 Dynamic Programming

 MDP assignment DUE (Friday)
9/30 Monte Carlo Methods SB 5.1--5.7 (you can skip Example 5.5)
 
10/3 Monte Carlo Methods
DP assignment DUE (Friday)
10/7 Temporal Difference Learning SB 6.1--6.8
 Project description OUT
10/10 Temporal Difference Learning

MC assignment DUE (Friday) 
10/14 No class (Columbus/Indigenous People's Day) 


10/17 Exam 1  
 
10/21 Planning and Learning SB 8.1--8.6;8.9--8.12
TD Learning assignment DUE (Monday)
10/24 Planning and Learning   

10/28 Linear Function Approximation  SB 9.1--9.5, 9.8, 10.1
 Project proposal DUE
10/31 Linear Function Approximation
Planning and Learning assignment DUE (Friday)
11/4 Deep Learning Overview/ DQN  GBC, 6.1--6.4, 9.1--9.3, Mnih, 2014 DQN, (optional background)
11/7 DQN and extensions Hasselt, 2015 (Double DQN), Schaul, 2016 (Prioritized Replay), Wang, 2015 (Dueling) Mnih, 2016 (A3C), Rainbow

Function assignment DUE (Friday)
11/11 No class (Veterans Day)

11/14 Policy gradient and actor critic  SB 13.1--13.7 DQN assignment DUE (Friday)
11/18 Deep policy gradient and actor critic Silver, 2014 (DPG), Lillicrap, 2016 (DDPG), Mnih, 2016 (A3C)
  
11/21 Advanced topics TBD  PG assignment DUE (Friday)
11/25 Exam 2 
 
11/28 No class (Thanksgiving)
 
12/2 Project Presentations
 
12/5
 Project Presentations



 


12/10
 Project Reports Due

Report due at 11:59 PM -- This is a hard deadline, no extensions


Important note: unless noted otherwise, all readings and assignments are due on the day that they appear in the schedule.