Skip to main content

Lecture Logistics

Lectures will be held in-person at 1-190 (campus map).

Lecture notes

Download link

2024 Course Schedule (tentative)

Event            Course DateLectureReadingLogistic
Lecture 1Feb. 06Introduction
slides
Lecture 2Feb. 08Simple Decision Making
slides
Bandits: Chapter 6, 7, 8, 9; Contextual Bandits: Chapter 18, 19; LinUCB: paper.
Lecture 3Feb. 13Simple Decision Making (from page 29) videoHW1 Released
Lecture 4Feb. 15Policy Gradient
slides
HolidayFeb. 20(No class)
Lecture 5Feb. 22Policy Gradient (from page 17)Horizon: paperHW2 Released
Lecture 6Feb. 27Policy Graident (from page 82)
Lexture 7Feb. 29Policy Gradient (from page 112)HW3 Released (Friday)
Lecture 8Mar. 05Policy Gradient (from page 127)
Reward Design & Shaping
slides
Lecture 9Mar. 07Learning from Demonstration
slides
HW4 Released (Friday)
Lecture 10Mar. 12Learning from Demonstration (from page 33)
Lecture 11Mar. 14Learning from Demonstration (from page 52)
Transfer from Simulation to Real World
slides
HW5 Released (Friday)
Lecture 12Mar. 19Transfer from Simulation to Real World (from page 32)
Lecture 13Mar. 21Transfer from Simulation to Real World (from page 124)
Model Learning
slides
Project Proposal Due, HW6 Released (Friday)
HolidayMar. 26Spring break
(No class)
HolidayMar. 28Spring break
(No class)
Lecture 14Apr. 02Model Learning (from page 43)
Lecture 15Apr. 04Model Learning (from page 69)
Tabular RL
slides
HW7 Released (Friday)
Lecture 16Apr. 09Tabular RL (from page 24)
Lecture 17Apr. 11Deep Q Learning
slides
HW8 Released (Friday)
Lecture 18Apr. 16Deep Q Learning (from page 48)
Lecture 19Apr. 18Special lecture
slides
Lecture 20Apr. 23Deep Q Learning (from page 60)
Lecture 21Apr. 25Offline Reinforcement Learning
slides
Project Midterm Report Due (Friday)
Lecture 22Apr. 30Multi-Task Learning
slides
Lecture 23May 02Multi-Task Learning (from page 24)
Lecture 24May 07Multi-Task Learning (from page 58)
Exploration in Reinforcement Learning
slides
Lecture 25May 09Wrapping Up
slides
Lecture 26May 14Project Presentations