CS 4/5789: Introduction to Reinforcement Learning

Lecture 4

Prof. Sarah Dean

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



0. Announcements & Recap

1. Value Iteration

2. Policy Iteration

3. Finite Horizon MDP

4. Dynamic Programming



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 due 2/14. Start early!


Optimal Policy & Bellman Optimality

Value Iteration

CS 4/5789: Lecture 4

By Sarah Dean


CS 4/5789: Lecture 4