Syllabus

Reading should be done after the associated lecture. Demonstrations during the lecture will be done in the Julia language using IJulia notebooks.

Date Topic Reading Due
Sep 25 Overview DMU 1
Sep 27 Probabilistic Representations DMU 2.1
Oct 2 Probabilistic Inference DMU 2.2
Oct 4 Parameter Learning DMU 2.3
Oct 6 Midterm 1 Review (NVIDIA Auditorium, 10:30am-11:20am)
Oct 9 Structure Learning DMU 2.4 Project 0
Oct 11 Midterm 1 (CEMEX Auditorium, 1:30pm-2:50pm)
Oct 16 Decision Theory and Games DMU 3.1-3.3
Oct 18 Markov Decision Processes DMU 4.1-4.4 Project 1
Oct 23 Approximate Dynamic Programming DMU 4.5-4.7
Oct 25 Exploration and Exploitation DMU 5.1
Oct 27 POMDPs.jl and Project 2 Review (NVIDIA Auditorium, 10:30am-11:20am) slides
Oct 30 Model-Based Reinforcement Learning DMU 5.2-5.3 Proposal
Nov 1 Model-Free Reinforcement Learning DMU 5.4-5.5
Nov 3 Midterm 2 Review (NVIDIA Auditorium, 10:30am-11:20am)
Nov 6 State Uncertainty DMU 6.1-6.2 Project 2
Nov 8 Midterm 2 (CEMEX Auditorium, 1:30pm-2:50pm)
Nov 13 Exact POMDP Methods DMU 6.3
Nov 15 Offline POMDP Methods DMU 6.4
Nov 20 Thanksgiving Week (no class)
Nov 22 Thanksgiving Week (no class)
Nov 27 Online POMDP Methods DMU 6.5
Nov 29 Deep Reinforcement Learning slides
Dec 4 Take-Home Midterm (no class)
Dec 6 Applications
Dec 9 Final Paper Due
Dec 11 Peer Review Due

Note: The dates for the various topics are approximate. Some topics may span multiple lectures. However, the schedule for the midterms will stay fixed.