Jan 19

Lecture 1

Introduction to Reinforcement Learning

Additional Reading:
High level introduction: Sutton and Barto Chp 1

Jan 21

Lecture 2

Basic probability theory review.

Additional Reading:
Review background materials on Basic Probability.
Notes on Basic Probability.

Jan 24

Assignment 1

Assignment 1 will be posted online.

Jan 26

Lecture 3

Markov Process, Markov Reward Process.

Additional Reading:
Sutton and Barto Chp 3

Jan 28

Lecture 4

Markov Decision Process, Policy Evaluation.

Additional Reading:
Sutton and Barto Chp 3, 4.1

Feb 2

Lecture 5

Policy Improvement, Policy Iteration, Value Iteration

Additional Reading:
Sutton and Barto Chp 4.2-4.4

Feb 4

Lecture 6

Policy Improvement, Policy Iteration, Value Iteration continued

Additional Reading:
Sutton and Barto Chp 4

Feb 9

Lecture 7

Monte Carlo and Time Difference Methods

Additional Reading:
Sutton and Barto Chp 5.1, 5.5, 6.1-6.3

Feb 11

Lecture 8

Monte Carlo and Time Difference Methods, Q-Learning

Additional Reading:
Sutton and Barto Chp 5.2, 5.4, 6.4-6.5, 6.7

Feb 12

Project Proposal Due

Project proposal due at midnight (i.e., 11:59 PM, 23:59) eastern time.

Feb 18

Assignment 1

Assignment 1 due at midnight (i.e., 11:59 PM, 23:59) eastern time.

Feb 21

Assignment 2

Assignment 2 will be posted online.

Feb 23

Lecture 9

Value Function Approximation

Additional Reading:
Sutton and Barto Chp 9.3, 9.6, 9.7

Feb 25

Lecture 10

Deep learning, CNNs, RNNs

Additional Reading:
Stanford's Deep Learning Notes
Ryerson's Deep Learning Course

Mar 2

Lecture 11

Deep learning, Deep Q-Learning

Additional Reading:
Stanford's Deep Learning Notes
Playing Atari with Deep RL

Mar 4

Lecture 12

Deep learning, Deep Q-Learning

Additional Reading:
Stanford's Deep Learning Notes
Playing Atari with Deep RL

Mar 9

Lecture 13

Imitation Learning

Additional Reading:
See slides on D2L.

Mar 11

Lecture 14

Policy Search

Additional Reading:
Sutton and Barto Chp 13

Mar 16

Lecture 15

Policy Search

Additional Reading:
Sutton and Barto Chp 13

Mar 18

Lecture 16

Multi-armed bandit. Exploration

Additional Reading:
Sutton and Barto Chp 2
Lattimore and Szepesvari Chp 7.1

Mar 19

Assignment 2

Assignment 2 due at midnight (i.e., 11:59 PM, 23:59) eastern time.

Mar 21

Assignment 3

Assignment 3 will be posted online.

Mar 23

Lecture 17

Exploration/Exploitation

Additional Reading:
Sutton and Barto Chp 2
Lattimore and Szepesvari Chp 35

Mar 25

Lecture 18

Batch Reinforcement Learning

Additional Reading:
See slides on D2L.

Mar 30

Lecture 19

Monte Carlo Tree Search

Additional Reading:
See slides on D2L.

Apr 1

Lecture 20

Inverse Reinforcement Learning

Additional Reading:
See slides on D2L.

Apr 6

Lecture 21

Transfer and Multi-Task Learning

Additional Reading:
See slides on D2L.

Apr 8

Lecture 22

Meta Learning

Additional Reading:
See slides on D2L.

Apr 13

Assignment 3

Assignment 3 due at midnight (i.e., 11:59 PM, 23:59) eastern time.

Apr 13

Lecture 23

Project presentations or advanced topics

Apr 15

Lecture 24

Project presentations or advanced topics

Apr 19

Final Project

Final Project report due at midnight (i.e., 11:59 PM, 23:59) eastern time.