CMPT 729: Reinforcement Learning

Reinforcement learning is the branch of machine learning that studies learning to act. Agents observe, predict, and act to change their environment. Reinforcement learning has notable success in learning to play games and control robots. In this course, we will cover fundamental concepts and algorithms, and introduce techniques that underlie many of the successes from reinforcement learning.

Instructor: Jason Peng (Office Hour: Fri 12:30-1:30pm TASC 9213)

TA: Zhen Li (Office Hour: Thu 3-4pm ASB 9810)

Lectures:
Wed 11:30am-12:20pm (AQ5037)
Fri 10:30am-12:20pm (AQ5037)

Grading

3 programming assignments (30%)

A1 (10%) - Due Sep 29
A2 (10%) - Due Oct 20
A3 (10%) - Due Nov 17

Paper presentation (20%)

Course project (50%)

Info
Proposal (10%) - Due Oct 20
- Template
Presentation (20%)
- Info
- Signup Sheet
Report (20%) - Due Dec 1
- Info
- Template

Late days: You have 3 late days that you can use for any assignment. You can distribute the late days however you like, but they can only be applied to programming assignments. Once you run out of late days, any late assignments will no longer be accepted.