CS 4/5789: Introduction to Reinforcement Learning

Lecture 3

Prof. Sarah Dean

MW 2:45-4pm
Zoom (110 Hollister Hall)

Agenda

 

0. Announcements & Recap

1. State-Action Distribution

2. Bellman Optimality

3. Value Iteration

Announcements

 

Register for participation (Canvas): PollEV.com/sarahdean011

 

I do not handle waitlist and enrollment.
Questions? cs-course-enroll@cornell.edu

 

Want to Audit? Ask (on Ed Discussion) after Add deadline.

 

HW0 released tonight, due in two weeks (2/14).

Recap

 

1. Markov Decision Process

2. Value and Q functions

3. Policy Evaluation

4. Approximate Policy Evaluation

5. State-Action Distribution

Infinite Horizon Discounted Markov Decision Process

Value and Q function

Bellman Equations

Policy Evaluation

State-action Distribution

Agenda

 

0. Announcements & Recap

1. State-Action Distribution

2. Bellman Optimality

3. Value Iteration