{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:19:28Z","timestamp":1775229568923,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004750","name":"Aeronautical Science Foundation of China","doi-asserted-by":"publisher","award":["20200058069001"],"award-info":[{"award-number":["20200058069001"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tg.2023.3263013","type":"journal-article","created":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T19:36:44Z","timestamp":1680118604000},"page":"270-281","source":"Crossref","is-referenced-by-count":14,"title":["Attention-Based Intrinsic Reward Mixing Network for Credit Assignment in Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9235-9429","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"first","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"}]},{"given":"Weiyan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4689-6140","authenticated-orcid":false,"given":"Shitong","family":"Shao","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"}]},{"given":"Shiyi","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1982-6780","authenticated-orcid":false,"given":"Aiguo","family":"Song","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref2","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2986005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56991-8_32"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683648"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CCAA.2017.8229841"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10205-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2018.8441797"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2020.02.017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2831240"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2022.3164242"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2022.3212201"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2901021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCNMC.2003.1243044"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref25","first-page":"1","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Foerster","year":"2016"},{"key":"ref26","first-page":"1","article-title":"Influence-based multi-agent exploration","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref27","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref29","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid","year":"2018"},{"key":"ref30","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":"ref31","first-page":"1","article-title":"Maven: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahajan","year":"2019"},{"key":"ref32","first-page":"1","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Du","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1177\/17298814211044946"},{"key":"ref34","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref36","first-page":"1","article-title":"AIIR-MIX: Multi-agent reinforcement learning meets attention individual intrinsic reward mixing network","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0271-y"},{"key":"ref38","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2886767"},{"key":"ref41","first-page":"1","article-title":"Attention-based models for speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chorowski","year":"2015"},{"key":"ref42","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","author":"Wang","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref46","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref47","article-title":"The StarCraft multi-agent challenge","author":"Samvelyan","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10559928\/10086649.pdf?arnumber=10086649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T21:28:40Z","timestamp":1719350920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10086649\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":48,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tg.2023.3263013","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}