Utilizing Hidden Observations to Enhance the Performance of the Trained Agent
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jang, Sooyoung | - |
dc.contributor.author | Lee, Joohyung | - |
dc.date.accessioned | 2022-09-27T06:40:32Z | - |
dc.date.available | 2022-09-27T06:40:32Z | - |
dc.date.created | 2022-09-22 | - |
dc.date.issued | 2022-07 | - |
dc.identifier.issn | 2377-3766 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/85575 | - |
dc.description.abstract | The frame-skipping strategy has been widely employed in deep reinforcement learning (DRL) technology to train an agent. Specifically, this strategy repeats the action determined by the agent for a fixed number of frames. It increases computational efficiency by reducing the number of inferences by making the action decision sparse. However, previously, these consecutive changes in frames during the frame-skipping were hidden and ignored from the environment and did not affect the agent's action decision. As a result, it can adversely affect the performance of trained agents, where the performance is more critical than computational efficiency. To alleviate these issues, we propose a new framework that utilizes these hidden frames during the frame-skipping, called hidden observation, to enhance the performance of the trained agent. The proposed framework retrieves all hidden observations during frame skipping. It then combines batch inference and an exponentially weighted sum to calculate and merge the outputs from hidden observations. Through experiments, we validated the effectiveness of the proposed method in terms of both performance and stability with only a marginal increase in computation. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.relation.isPartOf | IEEE ROBOTICS AND AUTOMATION LETTERS | - |
dc.title | Utilizing Hidden Observations to Enhance the Performance of the Trained Agent | - |
dc.type | Article | - |
dc.type.rims | ART | - |
dc.description.journalClass | 1 | - |
dc.identifier.wosid | 000838441200010 | - |
dc.identifier.doi | 10.1109/LRA.2022.3186508 | - |
dc.identifier.bibliographicCitation | IEEE ROBOTICS AND AUTOMATION LETTERS, v.7, no.3, pp.7858 - 7864 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-85133765546 | - |
dc.citation.endPage | 7864 | - |
dc.citation.startPage | 7858 | - |
dc.citation.title | IEEE ROBOTICS AND AUTOMATION LETTERS | - |
dc.citation.volume | 7 | - |
dc.citation.number | 3 | - |
dc.contributor.affiliatedAuthor | Lee, Joohyung | - |
dc.type.docType | Article | - |
dc.subject.keywordAuthor | AI-Enabled Robotics | - |
dc.subject.keywordAuthor | Robust/Adaptive Control | - |
dc.subject.keywordAuthor | Control Architectures and Programming | - |
dc.subject.keywordAuthor | Reinforcement Learning | - |
dc.relation.journalResearchArea | Robotics | - |
dc.relation.journalWebOfScienceCategory | Robotics | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
1342, Seongnam-daero, Sujeong-gu, Seongnam-si, Gyeonggi-do, Republic of Korea(13120)031-750-5114
COPYRIGHT 2020 Gachon University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.