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: Wed 4-5pm TASC 9213)

TA: Sha Hu (Office Hour: Fri 3-4pm Zoom)

Lectures:
    Wed 11:30am-12:20pm (SWH10051)
    Fri 10:30am-12:20pm (AQ5016)

Grading

3 programming assignments (30%)
Paper presentation (20%)
Course project (50%)
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.

Syllabus

Jan 10: Introduction
             

Jan 12: MDP
             

Jan 17: Snow Day (No Class)
             

Jan 19: Policy Evaluation
             

Jan 24: Behavioral Cloning
             

Jan 26: Behavioral Cloning, Policy Search
             

Jan 31: Policy Gradient
             

Feb 2: Policy Gradient
             

Feb 7: Q-Learning
             

Feb 9: Q-Learning
             

Feb 14: Actor-Critic Algorithms
             

Feb 16: Actor-Critic Algorithms, Model-Based RL
             

Feb 21: Reading Break (No Class)
             

Feb 23: Reading Break (No Class)
             

Feb 28: Model-Based RL
             

Mar 1: Model-Based RL, On-Policy vs Off-Policy Algorithms
             

Mar 6: Advance Policy Gradient
             

Mar 8: Advance Policy Gradient, Paper Presentations
             

Mar 13: Advance Q-Learning
             

Mar 15: Advance Q-Learning, Paper Presentations
             

Mar 20: Exploration
             

Mar 22: Exploration, Paper Presentations
             

Mar 27: Paper Presentations
             

Mar 29: Good Friday (No Class)
             

Apr 3: Domain Transfer, Paper Presentations
             

Apr 5: Domain Transfer, Project Presentations
             

Apr 10: Project Presentations
             

Apr 12: Project Presentations