Model Based Reinforcement Learning: Policy Iteration, Value Iteration, and Dynamic Programming - presented by Prof. Steven L. Brunton

Model Based Reinforcement Learning: Policy Iteration, Value Iteration, and Dynamic Programming

Speaker: Steven L. Brunton

-/27:09

Abstract

Speaker

AI Outline

Discussion

Model Based Reinforcement Learning: Policy Iteration, Value Iteration, and Dynamic Programming

Steven L. Brunton

University of Washington

Here we introduce dynamic programming, which is a cornerstone of model-based reinforcement learning. We demonstrate dynamic programming for policy iteration and value iteration, leading to the quality function and Q-learning.

References

1.
https://openlibrary.org/isbn/9781108422093

Reinforcement learning

Brunton Lab (University of Washington)

Cite as

S. L. Brunton (2022, January 7), Model Based Reinforcement Learning: Policy Iteration, Value Iteration, and Dynamic Programming

doi.org/10.52843/cassyni.6fs4s9

Share

Timestamped permalink

Details

Listed seminar This seminar is open to all

Recorded Available to all

Video length 27:09

Invited speaker series

Showcase your departmental research and attract collaborators, students and funders.