{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:15:29Z","timestamp":1740100529188,"version":"3.37.3"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science KAKENHI","doi-asserted-by":"publisher","award":["18K11483"],"award-info":[{"award-number":["18K11483"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,5]]},"DOI":"10.1109\/ssci50451.2021.9659877","type":"proceedings-article","created":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T21:09:51Z","timestamp":1643058591000},"page":"01-08","source":"Crossref","is-referenced-by-count":1,"title":["Swarm Reinforcement Learning Method Based on Hierarchical Q-Learning"],"prefix":"10.1109","author":[{"given":"Yasuaki","family":"Kuroe","sequence":"first","affiliation":[{"name":"Kansai University,Faculty of Engineering Science,Suita-shi,Osaka,Japan"}]},{"given":"Kenya","family":"Takeuchi","sequence":"additional","affiliation":[{"name":"Kansai University,Faculty of Engineering Science,Suita-shi,Osaka,Japan"}]},{"given":"Yutaka","family":"Maeda","sequence":"additional","affiliation":[{"name":"Kansai University,Faculty of Engineering Science,Suita-shi,Osaka,Japan"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/SMC.2013.393"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CEC.2015.7257266"},{"key":"ref12","first-page":"99","volume":"101","author":"kaelbling","year":"1998","journal-title":"Planning and acting in partially observable stochastic domains Artificial Intelligence"},{"key":"ref13","first-page":"2164","article-title":"Monte-Carlo planning in large POMDPs","volume":"23","author":"silver","year":"0","journal-title":"24th Annual Conference on Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1007\/s10458-012-9200-2"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1177\/105971239700600202"},{"key":"ref16","first-page":"279","volume":"8","author":"watkins","year":"1992","journal-title":"Q-learning Machine Learning"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1613\/jair.301"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/SICE.2006.315142"},{"year":"2001","author":"kennedy","journal-title":"Swarm Intelligence","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1007\/978-3-642-10684-2_19"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICSMC.2008.4811430"},{"key":"ref8","first-page":"905","article-title":"Swarm Reinforcement Learning Method for Multi-Agent Tasks -Solution of Dilemma Problems-","author":"yamawake","year":"0","journal-title":"Proceedings of SICE Annual Conference"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICSMC.2010.5642307"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-27645-3","article-title":"Reinforcement Learning State-of-the-Art","author":"wiering","year":"2012","journal-title":"Adaptation Learning and Optimization Book 12"},{"year":"1998","author":"sutton","journal-title":"Reinforcement Learning","key":"ref1"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICSMC.2011.6083999"}],"event":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","start":{"date-parts":[[2021,12,5]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2021,12,7]]}},"container-title":["2021 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9659537\/9659538\/09659877.pdf?arnumber=9659877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T18:37:17Z","timestamp":1683571037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9659877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/ssci50451.2021.9659877","relation":{},"subject":[],"published":{"date-parts":[[2021,12,5]]}}}