Course Overview

Foundations of and algorithms for reinforcment learning: decision theory, MDPs, basic and deep RL algorithms, and game theory

Info

Lectures are in person in Social Sciences 136. There are no plans to record lectures at this time. Attendance is strongly encouraged, but is, technically, optional. The readings will typically cover a superset of what I cover in lecture, the role of lecture is to emphasize and clarify the parts that I think are most important.

Instructor
Ron Parr
Office Hours: M 1-2 (in person), Tu 1-2 Zoom
Office: D209 LSRC
Phone: (919) 660-6537 (email preferred)
Email: parr at cs dot duke dot edu
Note: If I do not respond to email in 24 hours, it's just because I got burried in emails. Please email again if this happens.

TAs
Zechen Wu
Office Hours: W 11-1, location TBD
Zechen dot Wu at duke dot edu

Jianjun Ou
Office Hours: F 1-3 location TBD
Jianjun dot Ou at duke dot edu