Multi-agent reinforcement learning with approximate model learning for competitive games
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Young Joon | - |
dc.contributor.author | Cho, Yoon Sang | - |
dc.contributor.author | Kim, Seoung Bum | - |
dc.date.accessioned | 2021-09-01T06:15:10Z | - |
dc.date.available | 2021-09-01T06:15:10Z | - |
dc.date.created | 2021-06-19 | - |
dc.date.issued | 2019-09-11 | - |
dc.identifier.issn | 1932-6203 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/62880 | - |
dc.description.abstract | We propose a method for learning multi-agent policies to compete against multiple opponents. The method consists of recurrent neural network-based actor-critic networks and deterministic policy gradients that promote cooperation between agents by communication. The learning process does not require access to opponents' parameters or observations because the agents are trained separately from the opponents. The actor networks enable the agents to communicate using forward and backward paths while the critic network helps to train the actors by delivering them gradient signals based on their contribution to the global reward. Moreover, to address nonstationarity due to the evolving of other agents, we propose approximate model learning using auxiliary prediction networks for modeling the state transitions, reward function, and opponent behavior. In the test phase, we use competitive multi-agent environments to demonstrate by comparison the usefulness and superiority of the proposed method in terms of learning efficiency and goal achievements. The comparison results show that the proposed method outperforms the alternatives. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | PUBLIC LIBRARY SCIENCE | - |
dc.subject | FRAMEWORK | - |
dc.title | Multi-agent reinforcement learning with approximate model learning for competitive games | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Seoung Bum | - |
dc.identifier.doi | 10.1371/journal.pone.0222215 | - |
dc.identifier.scopusid | 2-s2.0-85072144072 | - |
dc.identifier.wosid | 000532188200041 | - |
dc.identifier.bibliographicCitation | PLOS ONE, v.14, no.9 | - |
dc.relation.isPartOf | PLOS ONE | - |
dc.citation.title | PLOS ONE | - |
dc.citation.volume | 14 | - |
dc.citation.number | 9 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Science & Technology - Other Topics | - |
dc.relation.journalWebOfScienceCategory | Multidisciplinary Sciences | - |
dc.subject.keywordPlus | FRAMEWORK | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
COPYRIGHT © 2021 Korea 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.