{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:19:34Z","timestamp":1775229574823,"version":"3.50.1"},"reference-count":37,"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":"crossref","award":["62372328"],"award-info":[{"award-number":["62372328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["22120240357"],"award-info":[{"award-number":["22120240357"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012247","name":"Program of Shanghai Academic Research Leader","doi-asserted-by":"publisher","award":["22XD1423700"],"award-info":[{"award-number":["22XD1423700"]}],"id":[{"id":"10.13039\/501100012247","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2022YFB4501704"],"award-info":[{"award-number":["2022YFB4501704"]}]},{"name":"Shanghai Science and Technology Innovation Action Plan Project","award":["22511100700"],"award-info":[{"award-number":["22511100700"]}]},{"name":"Open Fund of Key Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education","award":["2021FF08"],"award-info":[{"award-number":["2021FF08"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Soc. Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcss.2024.3428334","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T17:54:46Z","timestamp":1723053286000},"page":"7766-7777","source":"Crossref","is-referenced-by-count":4,"title":["Priority Over Quantity: A Self-Incentive Credit Assignment Scheme for Cooperative Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6814-3456","authenticated-orcid":false,"given":"Hao","family":"Tang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4752-0316","authenticated-orcid":false,"given":"Cheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1133-048X","authenticated-orcid":false,"given":"Shengbo","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4465-5880","authenticated-orcid":false,"given":"Junqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3074038"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3329990"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-28957-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3122282"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3297213"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3232390"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3409530"},{"key":"ref11","first-page":"1397","article-title":"Modeling difference rewards for multiagent learning","author":"Proper","year":"2012","journal-title":"Proc. 11th Int. Conf. Autonomous Agents Multiagent Syst. (AAMAS)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref13","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017"},{"key":"ref14","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rashid","year":"2018"},{"key":"ref15","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent q-learning","volume-title":"Proc. 9th Int. Conf. Learn. Representations (ICLR), Virtual Event","author":"Wang","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3100291"},{"key":"ref18","article-title":"Guided deep reinforcement learning for swarm systems","author":"H\u00fcttenrauch","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref20","first-page":"29","article-title":"Deep recurrent q-learning for partially observable MDPs","volume-title":"Proc. AAAI Fall Symp. Ser.","author":"Hausknecht","year":"2015"},{"key":"ref21","first-page":"27840","article-title":"Attention-based recurrence for multi-agent reinforcement learning under stochastic partial observability","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Phan","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6220"},{"key":"ref23","first-page":"10706","article-title":"Q-value path decomposition for deep multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2020"},{"key":"ref24","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu","year":"2022"},{"key":"ref25","first-page":"1046","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. 10th Int. Conf. Learn. Representations (ICLR)","author":"Kuba","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref28","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"He","year":"2016"},{"key":"ref29","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref30","first-page":"7613","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. (NeurIPS)","author":"Mahajan","year":"2019"},{"key":"ref31","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":"ref32","first-page":"1388","article-title":"A deep policy inference Q-network for multi-agent systems","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Hong","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref34","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Bellemare","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref36","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Schulman","year":"2015"},{"key":"ref37","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst. (AAMAS)","author":"Samvelyan","year":"2019"}],"container-title":["IEEE Transactions on Computational Social Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570650\/10772353\/10630533.pdf?arnumber=10630533","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T19:10:06Z","timestamp":1733253006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10630533\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":37,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcss.2024.3428334","relation":{},"ISSN":["2329-924X","2373-7476"],"issn-type":[{"value":"2329-924X","type":"electronic"},{"value":"2373-7476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}