{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T10:41:39Z","timestamp":1742380899203},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2014,5,17]],"date-time":"2014-05-17T00:00:00Z","timestamp":1400284800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2015,7]]},"DOI":"10.1007\/s10458-014-9265-1","type":"journal-article","created":{"date-parts":[[2014,5,16]],"date-time":"2014-05-16T19:50:06Z","timestamp":1400269806000},"page":"658-682","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Introducing decision entrustment mechanism into repeated bilateral agent interactions to achieve social optimality"],"prefix":"10.1007","volume":"29","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","published-online":{"date-parts":[[2014,5,17]]},"reference":[{"key":"9265_CR1","doi-asserted-by":"crossref","unstructured":"Airiau, S., & Sen, S. (2006). Learning to commit in repeated games. In AAMAS\u201906 (pp 1263\u20131265).","DOI":"10.1145\/1160633.1160861"},{"key":"9265_CR2","first-page":"11","volume":"10","author":"S Airiau","year":"2007","unstructured":"Airiau, S., & Sen, S. (2007). Evolutionary tournament-based comparison of learning and non-learning algorithms for iterated games. Journal of Artificial Societies and Social, Simulation, 10, 11.","journal-title":"Journal of Artificial Societies and Social, Simulation"},{"key":"9265_CR3","doi-asserted-by":"crossref","unstructured":"Banerjee, D., & Sen, S. (2007). Reaching pareto optimality in prisoner\u2019s dilemma using conditional joint action learning. In AAMAS\u201907 (pp 91\u2013108).","DOI":"10.1007\/s10458-007-0020-8"},{"key":"9265_CR4","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"MH Bowling","year":"2003","unstructured":"Bowling, M. H., & Veloso, M. M. (2003). Multiagent learning using a variable learning rate. Artificial Intelligence, 136, 215\u2013250.","journal-title":"Artificial Intelligence"},{"key":"9265_CR5","volume-title":"Theory of moves","author":"SJ Brams","year":"1994","unstructured":"Brams, S. J. (1994). Theory of moves. Cambridge: Cambridge University Press."},{"key":"9265_CR6","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1007\/s10458-013-9222-4","volume":"28","author":"D Chakraborty","year":"2013","unstructured":"Chakraborty, D., & Stone, P. (2013). Multiagent learning in the presence of memory-bounded agents. Autonomous Agents and Multi-Agent Systems, 28, 182\u2013213.","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"9265_CR7","unstructured":"Claus, C., & Boutilier, C. (1998). The dynamics of reinforcement learning in cooperative multiagent systems. In AAAI\u201998 (pp 746\u2013752)."},{"key":"9265_CR8","unstructured":"Crandall, J. W., & Goodrich, M. A. (2005). Learning to teach and follow in repeated games. In AAAI Workshop on Multiagent Learning."},{"key":"9265_CR9","volume-title":"The theory of learning in games","author":"D Fudenberg","year":"1998","unstructured":"Fudenberg, D., & Levine, D. K. (1998). The theory of learning in games. Cambridge, MA: MIT Press."},{"key":"9265_CR10","unstructured":"Hu, J., & Wellman, M. (1998). Multiagent reinforcement learning: Theoretical framework and an algorithm. In Proceedings of the Fifteenth International Conference on Machine Learning (pp 242\u2013250)."},{"key":"9265_CR11","unstructured":"Jafari, A., Greenwald, A., Gondek, D., & Ercal, G. (2001). On no-regret learning, fictitious play, and Nash equilibrium. In: ICML\u201901 (pp 226\u2013233)"},{"key":"9265_CR12","unstructured":"Jong, S., Tuyls, K., & Verbeeck, K. (2008). Artificial agents learning human fairness. In AAMAS\u201908, ACM Press (pp 863\u2013870)."},{"key":"9265_CR13","unstructured":"Lauer, M., & Rienmiller, M. (2000). An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In ICML\u201900 (pp 535\u2013542)."},{"key":"9265_CR14","doi-asserted-by":"crossref","unstructured":"Littman, M. (1994). Markov games as a framework for multi-agent reinforcement learning. In Proceedings of the 11th International Conference on Machine Learning (pp 322\u2013328).","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"9265_CR15","unstructured":"Littman, M. L., & Stone, P. (2001). Leading best-response strategies in repeated games. In IJCAI Workshop on Economic Agents, Models, and Mechanisms."},{"key":"9265_CR16","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.dss.2004.08.007","volume":"39","author":"ML Littman","year":"2005","unstructured":"Littman, M. L., & Stone, P. (2005). A polynomial time Nash equilibrium algorithm for repeated games. Decision Support Systems, 39, 55\u201366.","journal-title":"Decision Support Systems"},{"key":"9265_CR17","doi-asserted-by":"crossref","unstructured":"Moriyama, K. (2008). Learning-rate adjusting Q-learning for prisoner\u2019s dilemma games. In WI-IAT \u201908 (pp 322\u2013325).","DOI":"10.1109\/WIIAT.2008.170"},{"key":"9265_CR18","unstructured":"Oh, J., & Smith, S. F. (2008). A few good agents: multi-agent social learning. In AAMAS\u201908 (pp 339\u2013346)."},{"key":"9265_CR19","volume-title":"A course in game theory","author":"MJ Osborne","year":"1994","unstructured":"Osborne, M. J., & Rubinstein, A. (1994). A course in game theory. Cambridge: MIT Press."},{"key":"9265_CR20","unstructured":"Powers, R., & Shoham, Y. (2004). New criteria and a new algorithm for learning in multi-agent systems. In NIPS\u201904 17 (pp. 1089\u20131096)."},{"key":"9265_CR21","unstructured":"Powers, R., & Shoham, Y. (2005). Learning against opponents with bounded memory. In IJCAI\u201905 (pp 817\u2013822)."},{"key":"9265_CR22","doi-asserted-by":"crossref","unstructured":"Sen, S., Airiau, S., & Mukherjee, R. (2003). Towards a pareto-optimal solution in general-sum games. In AAMAS\u201903 (pp 153\u2013160).","DOI":"10.1145\/860575.860600"},{"key":"9265_CR23","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1016\/j.artint.2006.02.006","volume":"171","author":"Y Shoham","year":"2007","unstructured":"Shoham, Y., Powers, R., & Grenager, T. (2007). If multi-agent learning is the answer, what is the question? Artificial Intelligence, 171, 365\u2013377.","journal-title":"Artificial Intelligence"},{"key":"9265_CR24","unstructured":"Stimpson, J. L., Goodrich, M. A., Walters, L. C. (2001). Satisficing and learning cooperation in the prisoner\u2019s dilemma. In IJCAI\u201901 (pp 535\u2013540)."},{"key":"9265_CR25","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C. J. C. H., & Dayan, P. D. (1992). Q-learning. Machine Learning, 8, 279\u2013292.","journal-title":"Machine Learning"}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-014-9265-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10458-014-9265-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-014-9265-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T17:28:30Z","timestamp":1559150910000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10458-014-9265-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5,17]]},"references-count":25,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2015,7]]}},"alternative-id":["9265"],"URL":"https:\/\/doi.org\/10.1007\/s10458-014-9265-1","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,5,17]]}}}