{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:48:53Z","timestamp":1730270933307,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research, Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0103404"],"award-info":[{"award-number":["2020AAA0103404"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20220484077"],"award-info":[{"award-number":["20220484077"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341469","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"8054-8061","source":"Crossref","is-referenced-by-count":0,"title":["Deconfounded Opponent Intention Inference for Football Multi-Player Policy Learning"],"prefix":"10.1109","author":[{"given":"Shijie","family":"Wang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049"}]},{"given":"Yi","family":"Pan","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China,100190"}]},{"given":"Zhiqiang","family":"Pu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049"}]},{"given":"Boyin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049"}]},{"given":"Jianqiang","family":"Yi","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3124931"},{"key":"ref2","article-title":"Dynamic analysis of team strategy in professional football","volume":"13","author":"Shaw","year":"2019","journal-title":"Bar\u00e7 a sports analytics summit"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/02640414.2012.727455"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32060-6_34"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref6","article-title":"How does ai play football? an analysis of rl and real-world football strategies","author":"Scott","year":"2021","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2022.3186386"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/24748668.2013.11868691"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1037\/h0025720"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9309-1"},{"key":"ref11","first-page":"533","article-title":"Game theory-based opponent modeling in large imperfect-information games","volume-title":"The 10th International Conference on Autonomous Agents and Multiagent Systems-Volume 2","author":"Ganzfried","year":"2011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3233\/AIC-2009-0442"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-398532-3.00013-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v5i1.12348"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1086\/288105"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1111\/resp.12238"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1009211805"},{"key":"ref19","first-page":"12843","article-title":"Deconfounded value decomposition for multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref20","article-title":"Deconfounding reinforcement learning in observational settings","author":"Lu","year":"2018","journal-title":"arXiv preprint"},{"issue":"1","key":"ref21","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref22","first-page":"331","article-title":"Markov decision processes","volume-title":"Handbooks in operations research and management science","volume":"2","author":"Puterman","year":"1990"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3501714.3501738"},{"volume-title":"The book of why: the new science of cause and effect","year":"2018","author":"Pearl","key":"ref24"},{"key":"ref25","first-page":"3970","article-title":"Differentiable causal backdoor discovery","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Gultchin"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1214\/14-AOS1295"},{"key":"ref27","volume-title":"Sun Tzu: The art of war","volume":"39","author":"Griffith","year":"1963"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492900002919"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/362"},{"key":"ref30","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04898-2_327"},{"key":"ref32","article-title":"Dealing with non-stationarity in decentralized cooperative multi-agent deep reinforcement learning via multi-timescale learning","author":"Nekoei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref35","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11214-015-0169-4"},{"key":"ref37","article-title":"Qplex: Duplex dueling multi-agent q-learning","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref38","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Son"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341469.pdf?arnumber=10341469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T22:54:14Z","timestamp":1703026454000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341469","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}