{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:06:38Z","timestamp":1765357598954,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["62073323"],"award-info":[{"award-number":["62073323"]}],"id":[{"id":"10.13039\/501100001809","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":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcds.2024.3404061","type":"journal-article","created":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T17:46:05Z","timestamp":1716399965000},"page":"2055-2069","source":"Crossref","is-referenced-by-count":5,"title":["Long-Term and Short-Term Opponent Intention Inference for Football Multiplayer Policy Learning"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8429-9449","authenticated-orcid":false,"given":"Shijie","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4841-4048","authenticated-orcid":false,"given":"Zhiqiang","family":"Pu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5417-6013","authenticated-orcid":false,"given":"Yi","family":"Pan","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4391-9960","authenticated-orcid":false,"given":"Boyin","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9563-2518","authenticated-orcid":false,"given":"Hao","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3268-9482","authenticated-orcid":false,"given":"Jianqiang","family":"Yi","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"Schulman","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3239815"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3250819"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3246107"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms1580"},{"key":"ref7","first-page":"11853","article-title":"Learning implicit credit assignment for cooperative multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhou","year":"2020"},{"key":"ref8","first-page":"12 967","article-title":"Learning fair policies in decentralized cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zimmer","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191648"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00025-9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32060-6_34"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/24748668.2013.11868691"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1037\/h0025720"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9309-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2751963"},{"issue":"1","key":"ref18","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"article-title":"Dealing with non-stationarity in decentralized cooperative multi-agent deep reinforcement learning via multi-timescale learning","year":"2023","author":"Nekoei","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"article-title":"Value-decomposition networks for cooperative multi-agent learning","year":"2017","author":"Sunehag","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11214-015-0169-4"},{"article-title":"QPLEX: Duplex dueling multi-agent Q-learning","year":"2020","author":"Wang","key":"ref23"},{"key":"ref24","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3323987"},{"key":"ref26","article-title":"State augmentation via self-supervision in offline multi-agent reinforcement learning","author":"Wang","year":"2023","journal-title":"IEEE Trans. Cogn. Devel. Syst."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3281878"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3236599"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3186386"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2023.3345735"},{"key":"ref31","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/cav.1978"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207302"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/PRAI53619.2021.9551093"},{"key":"ref35","first-page":"61","article-title":"Opponent modeling in real-time strategy games","volume-title":"Proc. GAMEON","author":"Schadd","year":"2007"},{"key":"ref36","first-page":"533","article-title":"Game theory-based opponent modeling in large imperfect-information games","volume-title":"Proc. 10th Int. Conf. Auton. Agents Multiagent Syst.","volume":"2","author":"Ganzfried","year":"2011"},{"key":"ref37","first-page":"37","article-title":"Integrating opponent models with Monte-Carlo tree search in poker","volume-title":"Proc. Interactive Decision Theory and Game Theory","author":"Ponsen","year":"2010"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v31i1.16006"},{"key":"ref39","first-page":"2476","article-title":"A real-time opponent modeling system for rush football","volume-title":"Proc. 22nd Int. Joint Conf. Artif. Intell.","author":"Laviers","year":"2011"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v5i1.12348"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-398532-3.00013-0"},{"key":"ref43","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"He","year":"2016"},{"key":"ref44","first-page":"28208","article-title":"Model-based opponent modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341469"},{"key":"ref46","first-page":"331","article-title":"Markov decision processes","volume-title":"Handbooks in Operations Research and Management Science","volume":"2","author":"Puterman","year":"1990"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492900002919"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/362"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5555\/2986459.2986721"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmva.2006.03.007"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1002\/sdr.1505"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04898-2_327"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01138"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3207068"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10774064\/10536732.pdf?arnumber=10536732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T19:21:26Z","timestamp":1733340086000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10536732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":55,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2024.3404061","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"type":"print","value":"2379-8920"},{"type":"electronic","value":"2379-8939"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}