An expansion on prioritized experience replay with round robin scheduling

Angel I. Solis

doi:10.1117/12.2617502

31 May 2022 An expansion on prioritized experience replay with round robin scheduling

Angel I. Solis

Author Affiliations +

Proceedings Volume 12097, Big Data IV: Learning, Analytics, and Applications; 1209702 (2022) https://doi.org/10.1117/12.2617502
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Abstract

With the outstanding accomplishments achieved in recent years, Reinforcement Learning (RL) has become an area where researchers have flocked to in order to find innovative ideas and solutions to challenge and conquer some of the most difficult tasks. While the bulk of the research has been focused on the learning algorithms such as SARSA, Q-Learning, and Genetic, not much attention has been paid to tools used to help these algorithms (e.g. the Experience Replay Buffer). This paper goes over what is believed to be the most accurate Taxonomy of the AI field and briefly covers the Q-Learning algorithm, as it is the base algorithm for this study. Most importantly, it proposes a new Experience Replay Buffer technique, the Round Robin Prioritized Experience Replay Buffer (RRPERB), which aims to help RL agents learn quicker and generalize better to rarely seen states by not completely depriving them of experiences which are ranked as less priority.

Citation Download Citation

Angel I. Solis "An expansion on prioritized experience replay with round robin scheduling", Proc. SPIE 12097, Big Data IV: Learning, Analytics, and Applications, 1209702 (31 May 2022); https://doi.org/10.1117/12.2617502

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