Policy improvement in dynamic programming

Zhewen Zhang

doi:10.1117/12.2641811

10 November 2022 Policy improvement in dynamic programming

Zhewen Zhang

Proceedings Volume 12348, 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022); 123483Q (2022) https://doi.org/10.1117/12.2641811
Event: 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022), 2022, Zhuhai, China

Abstract

Policy improvement has a long history and is the essential element in dynamic programming. The general categories of policy improvement can be divided into four aspects including: heuristic methods, approximation methods, sampling methods and numerical improvement. Paralleling with the classic policy improvement methods, several variant tools are also introduced including Lambda Policy, Path Integral, High Confidence in Policy Improvement and Finite Sample Analysis for SARSA in linear function. Moreover, the introductions of those policy improvement methods, evaluation, and comparison between them are illustrated in this paper. There are totally three perspectives where this paper dissects the evaluation from training speed, sampling efficiency and methods ability.

Citation Download Citation

Zhewen Zhang "Policy improvement in dynamic programming", Proc. SPIE 12348, 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022), 123483Q (10 November 2022); https://doi.org/10.1117/12.2641811

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available