{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T03:54:25Z","timestamp":1768449265634,"version":"3.49.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412176","type":"proceedings-article","created":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T22:15:54Z","timestamp":1620252954000},"page":"9234-9241","source":"Crossref","is-referenced-by-count":2,"title":["Self-Play or Group Practice: Learning to Play Alternating Markov Game in Multi-Agent System"],"prefix":"10.1109","author":[{"given":"Chin-Wing","family":"Leung","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuyue","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ho-Fung","family":"Leung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2019.8790141"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/523"},{"key":"ref33","first-page":"1188","article-title":"Evolution-guided policy gradient in reinforcement learning","author":"khadka","year":"2018","journal-title":"NIPS"},{"key":"ref32"},{"key":"ref31"},{"key":"ref30","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"ICML JMLR org"},{"key":"ref37","article-title":"Generalized markov decision processes: Dynamic-programming and reinforcement-learning algorithms","volume":"96","author":"szepesv\u00e1ri","year":"1996","journal-title":"ICML"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref35","first-page":"1100","article-title":"Simultaneously learning and advising in multiagent reinforcement learning","author":"da silva","year":"2017","journal-title":"AAMAS"},{"key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32937-1_19"},{"key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref13"},{"key":"ref14","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/1318484"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21061\/jte.v7i1.a.2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2007.11.006"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/acp.1834"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref28","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"AAAI"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","article-title":"A comprehensive survey of multiagent reinforcement learning","volume":"38","author":"bu","year":"2008","journal-title":"IEEE Trans Syst Man Cybern Part C Appl Rev"},{"key":"ref3","first-page":"5360","article-title":"Thinking fast and slow with deep learning and tree search","author":"anthony","year":"2017","journal-title":"NIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam6960"},{"key":"ref8"},{"key":"ref7","article-title":"Provable self-play algorithms for competitive reinforcement learning","author":"bai","year":"0","journal-title":"Proceedings of ICML 2020"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-0143-1"},{"key":"ref1","first-page":"22","article-title":"Is multiagent deep reinforcement learning the answer or the question? a brief survey","volume":"21","author":"hernandez-leal","year":"2018","journal-title":"Learning"},{"key":"ref46","first-page":"230","article-title":"New winning and losing positions for 7 × 7 hex","author":"yang","year":"2002","journal-title":"ICCG"},{"key":"ref20","first-page":"310","article-title":"A generalized reinforcement-learning model: Convergence and applications","volume":"96","author":"littman","year":"1996","journal-title":"ICML"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2010.2067212"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1006\/jeth.2000.2785"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.2307\/1911700"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3233\/ICG-1988-11410"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016070"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2014.2367105"},{"key":"ref23","first-page":"193","article-title":"Extensive games and the problem of information, contributions to the theory of games ii","volume":"28","author":"kuhn","year":"1953","journal-title":"Annals of Mathematics Studies"},{"key":"ref44"},{"key":"ref26","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"hu","year":"2003","journal-title":"JMLR"},{"key":"ref43","author":"nash","year":"1952","journal-title":"Some games and machines for playing them"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","location":"Milan, Italy","start":{"date-parts":[[2021,1,10]]},"end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412176.pdf?arnumber=9412176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:46Z","timestamp":1652182846000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412176","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}