{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T09:25:13Z","timestamp":1725701113708},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642326943"},{"type":"electronic","value":"9783642326950"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-32695-0_10","type":"book-chapter","created":{"date-parts":[[2012,8,25]],"date-time":"2012-08-25T16:46:00Z","timestamp":1345913160000},"page":"88-99","source":"Crossref","is-referenced-by-count":6,"title":["Learning to Achieve Socially Optimal Solutions in General-Sum Games"],"prefix":"10.1007","author":[{"given":"Jianye","family":"Hao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ho-fung","family":"Leung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Banerjee, D., Sen, S.: Reaching pareto optimality in prisoner\u2019s dilemma using conditional joint action learning. In: AAMAS 2007, pp. 91\u2013108 (2007)","DOI":"10.1007\/s10458-007-0020-8"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Bowling, M.H., Veloso, M.M.: Multiagent learning using a variable learning rate. In: Artificial Intelligence, pp. 215\u2013250 (2003)","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"10_CR3","volume-title":"Theory of Moves","author":"S.J. Brams","year":"1994","unstructured":"Brams, S.J.: Theory of Moves. Cambridge University Press, Cambridge (1994)"},{"key":"10_CR4","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1006\/jeth.2002.2927","volume":"104","author":"C.F. Camerer","year":"2002","unstructured":"Camerer, C.F., Ho, T.H., Chong, J.K.: Sophisticated ewa learning and strategic teaching in repeated games. Journal of Economic Theory\u00a0104, 137\u2013188 (2002)","journal-title":"Journal of Economic Theory"},{"key":"10_CR5","unstructured":"Crandall, J.W., Goodrich, M.A.: Learning to teach and follow in repeated games. In: AAAI Workshop on Multiagent Learning (2005)"},{"key":"10_CR6","unstructured":"Fudenberg, D., Levine, D.K.: The Theory of Learning in Games. MIT Press (1998)"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Hao, J.Y., Leung, H.F.: Strategy and fairness in repeated two-agent interaction. In: ICTAI 2010, pp. 3\u20136. IEEE Computer Society (2010)","DOI":"10.1109\/ICTAI.2010.75"},{"key":"10_CR8","unstructured":"Jafari, A., Greenwald, A., Gondek, D., Ercal, G.: On no-regret learning, fictitious play, and nash equilibrium. In: ICML 2001, pp. 226\u2013233 (2001)"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Littman, M.: Markov games as a framework for multi-agent reinforcement learning. In: ICML 1994, pp. 322\u2013328 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"10_CR10","unstructured":"Littman, M.L., Stone, P.: Leading best-response strategies in repeated games. In: IJCAI Workshop on Economic Agents, Models, and Mechanisms (2001)"},{"key":"10_CR11","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.dss.2004.08.007","volume":"39","author":"M.L. Littman","year":"2005","unstructured":"Littman, M.L., Stone, P.: A polynomial time nash equilibrium algorithm for repeated games. Decision Support Systems\u00a039, 55\u201366 (2005)","journal-title":"Decision Support Systems"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Moriyama, K.: Learning-rate adjusting q-learning for prisoner\u2019s dilemma games. In: WI-IAT 2008. pp. 322\u2013325 (2008)","DOI":"10.1109\/WIIAT.2008.170"},{"key":"10_CR13","unstructured":"oH, J., Smith, S.F.: A few good agents: multi-agent social learning. In: AAMAS 2008, pp. 339\u2013346 (2008)"},{"key":"10_CR14","volume-title":"A Course in Game Theory","author":"M.J. Osborne","year":"1994","unstructured":"Osborne, M.J., Rubinstein, A.: A Course in Game Theory. MIT Press, Cambridge (1994)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Sen, S., Airiau, S., Mukherjee, R.: Towards a pareto-optimal solution in general-sum games. In: AAMAS 2003, pp. 153\u2013160 (2003)","DOI":"10.1145\/860596.860600"},{"key":"10_CR16","unstructured":"Stimpson, J.L., Goodrich, M.A., Walters, L.C.: Satisficing and learning cooperation in the prisoner\u2019s dilemma. In: IJCAI 2001, pp. 535\u2013540 (2001)"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Watkins, C.J.C.H., Dayan, P.D.: Q-learning. In: Machine Learning, pp. 279\u2013292 (1992)","DOI":"10.1023\/A:1022676722315"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2012: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-32695-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T01:13:08Z","timestamp":1558314788000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-32695-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642326943","9783642326950"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-32695-0_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}