{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T19:55:19Z","timestamp":1790970919465,"version":"4.1.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62503395"],"award-info":[{"award-number":["62503395"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Soc. Syst."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tcss.2026.3705509","type":"journal-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T19:46:42Z","timestamp":1782503202000},"page":"5595-5607","source":"Crossref","is-referenced-by-count":0,"title":["Learning Multiagent Cooperation via Reciprocity-Based Actor-Critic Framework"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3358-3647","authenticated-orcid":false,"given":"Jia","family":"Long","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University","place":["Xi\u2019an, China"],"department":["School of Mechanical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1803-3946","authenticated-orcid":false,"given":"Dengxiu","family":"Yu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University","place":["Xi\u2019an, China"],"department":["School of Artificial Intelligence, Optics and Electronics (iOPEN)"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[{"name":"South China University of Technology","place":["Guangzhou, China"],"department":["School of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604669"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2025.3548476"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0495"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128514"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2025.3589373"},{"key":"ref7","article-title":"Pareto actor-critic for equilibrium selection in multi-agent reinforcement learning","author":"Christianos","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185549"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.65109\/RVSE8744"},{"key":"ref10","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2024.3401000"},{"key":"ref12","article-title":"Learning altruistic behaviours in reinforcement learning without external rewards","author":"Franzmeyer","year":"2021"},{"issue":"178","key":"ref13","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1421"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1093\/jeea\/jvae042"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2024.3428334"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095800"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-024-06700-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"issue":"2","key":"ref21","first-page":"25817","article-title":"Scalable multi-agent reinforcement learning through intelligent information aggregation","volume":"2","author":"Nayak","year":"2023","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref22","first-page":"849","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume":"29","author":"Kulkarni","year":"2016","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/488"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.65109\/HMVE9255"},{"key":"ref25","article-title":"Advantage alignment algorithms","author":"Duque","year":"2024"},{"issue":"1","key":"ref26","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1787"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3389555"},{"key":"ref29","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","author":"Kuba","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399095"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.65109\/qdcv6054"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3575196"},{"key":"ref33","article-title":"SocialJax: An evaluation suite for multi-agent reinforcement learning in sequential social dilemmas","author":"Guo","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3620954"},{"key":"ref35","first-page":"3326","article-title":"Inequity aversion improves cooperation in intertemporal social dilemmas","volume":"31","author":"Hughes","year":"2018","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447262"},{"key":"ref37","first-page":"36435","article-title":"Revisiting cooperative off-policy multi-agent reinforcement learning","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Li","year":"2025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3630058"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/34"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01758-5"},{"key":"ref41","first-page":"980","article-title":"Deep coordination graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"B\u00f6hmer","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1214\/23-AAP1949"},{"key":"ref43","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"}],"container-title":["IEEE Transactions on Computational Social Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570650\/11718796\/11581306.pdf?arnumber=11581306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T19:08:55Z","timestamp":1790968135000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11581306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":43,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcss.2026.3705509","relation":{},"ISSN":["2329-924X"],"issn-type":[{"value":"2329-924X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}