{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:19:48Z","timestamp":1777889988866,"version":"3.51.4"},"reference-count":29,"publisher":"SAGE Publications","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["WEB"],"published-print":{"date-parts":[[2015,8,18]]},"DOI":"10.3233\/web-150319","type":"journal-article","created":{"date-parts":[[2015,8,26]],"date-time":"2015-08-26T11:29:11Z","timestamp":1440588551000},"page":"167-178","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement social learning of social optimality with influencer agents"],"prefix":"10.1177","volume":"13","author":[{"given":"Jianye","family":"Hao","sequence":"first","affiliation":[{"name":"School of Software, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ho-Fung","family":"Leung","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong. E-mails:\u00a0jianye@mit.edu,\u00a0lhf@cse.cuhk.edu.hk"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"issue":"2","key":"10.3233\/WEB-150319_ref1","first-page":"85","article-title":"On the stability of a dynamic stochastic capacity pricing scheme for resource allocation in a multi-agent environment","volume":"3","author":"Anyouzoa","year":"2005","journal-title":"Web Intelligence and Agent Systems"},{"key":"10.3233\/WEB-150319_ref2","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","article-title":"Multiagent learning using a variable learning rate","volume":"136","author":"Bowling","year":"2002","journal-title":"Artificial Intelligence"},{"key":"10.3233\/WEB-150319_ref3","doi-asserted-by":"crossref","unstructured":"[3]I.\u00a0Chao, O.\u00a0Ardaiz and R.\u00a0Sanguesa, Tag mechanisms evaluated for coordination in open multi-agent systems, in: Proc. of ESAW\u201907, 2008, pp.\u00a0254\u2013269.","DOI":"10.1007\/978-3-540-87654-0_14"},{"key":"10.3233\/WEB-150319_ref4","unstructured":"[4]H.\u00a0Franks, N.\u00a0Griffiths and S.S.\u00a0Anand, Learning influence in complex social networks, in: Proc. of AAMAS\u201913, ACM Press, 2013, pp.\u00a0447\u2013454."},{"key":"10.3233\/WEB-150319_ref6","unstructured":"[6]D.\u00a0Fudenberg and D.K.\u00a0Levine, The Theory of Learning in Games, MIT Press, 1998."},{"issue":"1","key":"10.3233\/WEB-150319_ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3233\/WIA-2010-0177","article-title":"Collective iterative allocation: Enabling fast and optimal group decision making the role of group knowledge, optimism, and decision policies in distributed coordination","volume":"8","author":"Guttmann","year":"2010","journal-title":"Web Intelligence and Agent Systems"},{"key":"10.3233\/WEB-150319_ref8","doi-asserted-by":"crossref","unstructured":"[8]D.\u00a0Hales and B.\u00a0Edmonds, Evolving social rationality for mas using \u201ctags\u201d, in: Proc. of AAMAS\u201903, ACM Press, 2003, pp.\u00a0497\u2013503.","DOI":"10.1145\/860653.860655"},{"issue":"3","key":"10.3233\/WEB-150319_ref9","first-page":"15","article-title":"Achieving socially optimal outcomes in multiagent systems with reinforcement social learning","volume":"8","author":"Hao","year":"2013","journal-title":"ACM Transactions on Autonomous and Adaptive Systems (TAAS)"},{"key":"10.3233\/WEB-150319_ref10","doi-asserted-by":"crossref","unstructured":"[10]J.Y.\u00a0Hao and H.F.\u00a0Leung, Learning to achieve social rationality using tag mechanism in repeated interactions, in: Proc. of ICTAI\u201911, 2011, pp.\u00a0148\u2013155.","DOI":"10.1109\/ICTAI.2011.31"},{"key":"10.3233\/WEB-150319_ref11","doi-asserted-by":"crossref","unstructured":"[11]J.Y.\u00a0Hao and H.F.\u00a0Leung, Learning to achieve socially optimal solutions in general-sum game, in: Proc. of PRICAI\u201912, 2012, pp.\u00a088\u201399.","DOI":"10.1007\/978-3-642-32695-0_10"},{"key":"10.3233\/WEB-150319_ref12","unstructured":"[12]L.M.\u00a0Hogg and N.R.\u00a0Jennings, Socially rational agents, in: Proc. of AAAI Fall Symposium on Socially Intelligent Agents, 1997, pp.\u00a061\u201363."},{"key":"10.3233\/WEB-150319_ref13","unstructured":"[13]J.\u00a0Hu and M.\u00a0Wellman, Multiagent reinforcement learning: Theoretical framework and an algorithm, in: Proc. of ICML\u201998, 1998, pp.\u00a0242\u2013250."},{"issue":"2","key":"10.3233\/WEB-150319_ref14","first-page":"139","article-title":"Design, implementation and run-time evolution of a mission-based multiagent system","volume":"5","author":"Jayaputera","year":"2007","journal-title":"Web Intelligence and Agent Systems"},{"issue":"2","key":"10.3233\/WEB-150319_ref15","first-page":"105","article-title":"Asymmetric multiagent reinforcement learning","volume":"2","author":"K\u00f6n\u00f6nen","year":"2004","journal-title":"Web Intelligence and Agent Systems"},{"issue":"1","key":"10.3233\/WEB-150319_ref16","first-page":"17","article-title":"Gradient descent for symmetric and asymmetric multiagent reinforcement learning","volume":"3","author":"K\u00f6n\u00f6nen","year":"2005","journal-title":"Web Intelligence and Agent Systems"},{"issue":"4","key":"10.3233\/WEB-150319_ref17","first-page":"231","article-title":"Hybrid negotiation for resource coordination in multiagent systems","volume":"3","author":"Li","year":"2005","journal-title":"Web Intelligence and Agent Systems"},{"key":"10.3233\/WEB-150319_ref18","unstructured":"[18]M.\u00a0Littman, Markov games as a framework for multi-agent reinforcement learning, in: Proc. of ICML\u201994, 1994, pp.\u00a0322\u2013328."},{"key":"10.3233\/WEB-150319_ref19","doi-asserted-by":"crossref","unstructured":"[19]M.\u00a0Matlock and S.\u00a0Sen, Effective tag mechanisms for evolving coordination, in: Proc. of AAMAS\u201907, 2007, pp.\u00a01\u20138.","DOI":"10.1145\/1329125.1329429"},{"key":"10.3233\/WEB-150319_ref20","unstructured":"[20]M.\u00a0Matlock and S.\u00a0Sen, Effective tag mechanisms for evolving cooperation, in: Proc. of AAMAS\u201909, 2009, pp.\u00a0489\u2013496."},{"key":"10.3233\/WEB-150319_ref21","doi-asserted-by":"crossref","unstructured":"[21]M.\u00a0Matlock and S.\u00a0Sen, The success and failure of tag-mediated evolution of cooperation, in: Proc. of LAMAS, Springer, 2005, pp.\u00a0155\u2013164.","DOI":"10.1007\/11691839_9"},{"issue":"3","key":"10.3233\/WEB-150319_ref22","first-page":"185","article-title":"Modelling social behavior with a socio psychological simulation approach","volume":"2","author":"Mosler","year":"2004","journal-title":"Web Intelligence and Agent Systems"},{"key":"10.3233\/WEB-150319_ref23","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/364056a0","article-title":"A strategy of winstay, lose-shit that outperforms tit-for-tat in the prisoner\u2019s dilemma game","volume":"364","author":"Nowak","year":"1993","journal-title":"Nature"},{"issue":"3","key":"10.3233\/WEB-150319_ref24","first-page":"187","article-title":"A multi-agent system integrating reinforcement learning, bidding and genetic algorithms","volume":"1","author":"Qi","year":"2003","journal-title":"Web Intelligence and Agent Systems"},{"issue":"2","key":"10.3233\/WEB-150319_ref25","first-page":"97","article-title":"Many is more: The utility of simple reactive agents with predictive mechanisms in multiagent object collection tasks","volume":"3","author":"Scheutz","year":"2005","journal-title":"Web Intelligence and Agent Systems"},{"key":"10.3233\/WEB-150319_ref26","unstructured":"[26]S.\u00a0Sen and S.\u00a0Airiau, Emergence of norms through social learning, in: Proc. of IJCAI\u201907, 2007, pp.\u00a01507\u20131512."},{"issue":"3","key":"10.3233\/WEB-150319_ref27","doi-asserted-by":"crossref","first-page":"313","DOI":"10.3233\/WIA-2008-0143","article-title":"Investigating adaptive, confidence-based strategic negotiations in complex multiagent environments","volume":"6","author":"Soh","year":"2008","journal-title":"Web Intelligence and Agent Systems"},{"issue":"3","key":"10.3233\/WEB-150319_ref28","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1162\/artl.1995.2.3.319","article-title":"A self-organizing spatial vocabulary","volume":"2","author":"Steels","year":"1995","journal-title":"Artificial Life"},{"key":"10.3233\/WEB-150319_ref29","doi-asserted-by":"crossref","unstructured":"[29]D.\u00a0Villatoro, S.\u00a0Sen and J.\u00a0Sabater-Mir, Topology and memory effect on convention emergence, in: Proc. of WI-IAT\u201909, 2009, pp.\u00a0233\u2013240.","DOI":"10.1109\/WI-IAT.2009.155"},{"key":"10.3233\/WEB-150319_ref30","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/s101640170010","article-title":"A simple learning strategy that realizes robust cooperation better than pavlov in iterated prisoner\u2019s dilemma","volume":"19","author":"Wakano","year":"2001","journal-title":"J. Ethology"}],"container-title":["Web Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/WEB-150319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:26:52Z","timestamp":1777613212000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/WEB-150319"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,8,18]]},"references-count":29,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3233\/web-150319","relation":{},"ISSN":["2405-6464","2405-6456"],"issn-type":[{"value":"2405-6464","type":"electronic"},{"value":"2405-6456","type":"print"}],"subject":[],"published":{"date-parts":[[2015,8,18]]}}}