{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:14:17Z","timestamp":1740179657102,"version":"3.37.3"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12001220"],"award-info":[{"award-number":["12001220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tg.2022.3177598","type":"journal-article","created":{"date-parts":[[2022,5,24]],"date-time":"2022-05-24T19:43:15Z","timestamp":1653421395000},"page":"360-367","source":"Crossref","is-referenced-by-count":0,"title":["Dynamically Interrupting Deadlocks in Game Learning Using Multisampling Multiarmed Bandits"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3901-9708","authenticated-orcid":false,"given":"Rendong","family":"Chen","sequence":"first","affiliation":[{"name":"School of Mathematical Sciences, Qufu Normal University, Qufu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fa","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang Demetics Medical Technology Co., Ltd., Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref35","first-page":"23","article-title":"Online learning with feedback graphs: Beyond bandits","volume":"40","author":"alon","year":"0","journal-title":"Proc J Mach Learn Res Workshop Conf"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1952-09620-8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/140989455"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2015.47"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176350495"},{"article-title":"Solving planning problems with deep reinforcement learning and tree search","year":"2018","author":"ge","key":"ref36"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/304"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11629"},{"article-title":"Evolving a compact concept-based Sokoban solver","year":"2005","author":"schaul","key":"ref11"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/socs.v12i1.18580"},{"key":"ref10","first-page":"1","article-title":"Towards deadlock free Sokoban","author":"cazenave","year":"0","journal-title":"Proc 13th Board Game Stud Colloq"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93842-0_11"},{"article-title":"Modification of UCT with patterns in Monte-Carlo Go","year":"2006","author":"gelly","key":"ref2"},{"article-title":"Temporal credit assignment in reinforcement learning","year":"1984","author":"sutton","key":"ref1"},{"article-title":"A survey of online experiment design with the stochastic multi-armed bandit","year":"2015","author":"burtini","key":"ref17"},{"key":"ref39","first-page":"5690","article-title":"Imagination-augmented agents for deep reinforcement learning","volume":"30","author":"racani\u00e8re","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref38","first-page":"65","article-title":"Sokoban is pspace-complete","volume":"4","author":"culberson","year":"0","journal-title":"Proc Inform"},{"key":"ref19","first-page":"335","article-title":"High-probability regret bounds for bandit online linear optimization","author":"bartlett","year":"0","journal-title":"Proc 21st Annu Conf Learn Theory"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1561\/2200000024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2011.6140047"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-009-0318-1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87987-9_25"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1250790.1250807"},{"key":"ref20","first-page":"19","article-title":"Contextual bandit algorithms with supervised learning guarantees","author":"beygelzimer","year":"0","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17572-5_12"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1134707.1134736"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8279"},{"key":"ref27","first-page":"1054","article-title":"Non-stochastic bandit slate problems","author":"kale","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8637"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1066677.1066685"},{"journal-title":"Incorporating Prior Knowledge and Previously Learned Information Into Reinforcement Learning Agents","year":"2000","author":"dixon","key":"ref7"},{"key":"ref9","first-page":"27","article-title":"Sokoban: A challenging single-agent search problem","author":"junghanns","year":"0","journal-title":"Proc Int Joint Conf Artif Intell Workshop Games Exp Testbed AI Res"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"ref3","first-page":"282","article-title":"Bandit based Monte-Carlo planning","author":"kocsis","year":"0","journal-title":"Proc Eur Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(92)90028-V"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-64575-6_36"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"schulman","key":"ref40"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10251473\/09780537.pdf?arnumber=9780537","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T18:12:47Z","timestamp":1696270367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9780537\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":40,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tg.2022.3177598","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}