{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T19:59:07Z","timestamp":1725566347841},"publisher-location":"Berlin, Heidelberg","reference-count":26,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540231059"},{"type":"electronic","value":"9783540301158"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2004]]},"DOI":"10.1007\/978-3-540-30115-8_18","type":"book-chapter","created":{"date-parts":[[2010,9,18]],"date-time":"2010-09-18T03:24:16Z","timestamp":1284780256000},"page":"168-179","source":"Crossref","is-referenced-by-count":8,"title":["Analyzing Multi-agent Reinforcement Learning Using Evolutionary Dynamics"],"prefix":"10.1007","author":[{"given":"Pieter","family":"Jan\u2019t Hoen","sequence":"first","affiliation":[]},{"given":"Karl","family":"Tuyls","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Banerjee, B., Peng, J.: Adaptive policy gradient in multiagent learning. In: AAMAS (2003)","DOI":"10.1145\/860575.860686"},{"key":"18_CR2","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1022140919877","volume":"13","author":"A. Barto","year":"2003","unstructured":"Barto, A., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Discrete-Event Systems journal, Special issue on Reinforcement Learning\u00a013, 41\u201377 (2003)","journal-title":"Discrete-Event Systems journal, Special issue on Reinforcement Learning"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Becker, R., Zilberstein, S., Lesser, V., Goldman, C.V.: Transition-independent decentralized Markov decision problems. In: AAMAS (2003)","DOI":"10.1145\/860581.860583"},{"key":"18_CR4","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: AAAI\/IAAI, pp. 746\u2013752 (1998)"},{"key":"18_CR5","volume-title":"Game Theory Evolving","author":"C. Gintis","year":"2000","unstructured":"Gintis, C.: Game Theory Evolving. Princeton University Press, Princeton (2000)"},{"key":"18_CR6","unstructured":"Grenager, T., Powers, R., Shoham, Y.: Dispersion games: general definitions and some specific learning results. In: AAAI 2002 (2002)"},{"key":"18_CR7","unstructured":"Guestrin, C., Koller, D., Gearhart, C., Kanodia, N.: Generalizing plans to new environments in relational MDPs. In: International Joint Conference on Artificial Intelligence, IJCAI 2003 (2003)"},{"key":"18_CR8","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139173179","volume-title":"Evolutionary Games and Population Dynamics","author":"J. Hofbauer","year":"1998","unstructured":"Hofbauer, J., Sigmund, K.: Evolutionary Games and Population Dynamics. Cambridge University Press, Cambridge (1998)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Huang, P., Sycara, K.: Multi-agent learning in extensive games with complete information. In: AAMAS (2003)","DOI":"10.1145\/860575.860688"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Jung, H., Tambe, M.: Performance model for large scale multiagent systems. In: AAMAS (2003)","DOI":"10.1145\/860575.860623"},{"key":"18_CR11","first-page":"535","volume-title":"Proc. 17th International Conf. on Machine Learning","author":"M. Lauer","year":"2000","unstructured":"Lauer, M., Riedmiller, M.: An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In: Proc. 17th International Conf. on Machine Learning, pp. 535\u2013542. Morgan Kaufmann, San Francisco (2000)"},{"key":"18_CR12","volume-title":"A Course in Game Theory","author":"M. Osborne","year":"1994","unstructured":"Osborne, M., Rubinstein, A.: A Course in Game Theory. The MIT Press, Cambridge (1994)"},{"key":"18_CR13","volume-title":"Evolutionary Games and Equilibrium Selection","author":"L. Samuelson","year":"1997","unstructured":"Samuelson, L.: Evolutionary Games and Equilibrium Selection. MIT Press, Cambridge (1997)"},{"key":"18_CR14","doi-asserted-by":"publisher","first-page":"2794","DOI":"10.1093\/nar\/28.14.2794","volume":"28","author":"T. Schneider","year":"2000","unstructured":"Schneider, T.: Evolution of biological information. journal of NAR\u00a028, 2794\u20132799 (2000)","journal-title":"journal of NAR"},{"key":"18_CR15","unstructured":"Stauffer, D.: Life, love and death: Models of biological reproduction and aging. Institute for Theoretical physics, K\u00f6ln, Euroland (1999)"},{"key":"18_CR16","volume-title":"Reinforcement learning: An introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement learning: An introduction. MIT Press, Cambridge (1998)"},{"key":"18_CR17","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/978-3-540-39857-8_18","volume-title":"Machine Learning: ECML 2003","author":"P. Hoen \u2019t","year":"2003","unstructured":"\u2019t Hoen, P., Bohte, S.: COllective INtelligence with sequences of actions. In: Lavra\u010d, N., Gamberger, D., Todorovski, L., Blockeel, H. (eds.) ECML 2003. LNCS (LNAI), vol.\u00a02837, pp. 181\u2013192. Springer, Heidelberg (2003)"},{"key":"18_CR18","series-title":"Lecture Notes in Artificial Intelligence","volume-title":"Proceedings of CDOCS 2003","author":"P. Hoen \u2019t","year":"2003","unstructured":"\u2019t Hoen, P., Bohte, S.: COllective INtelligence with task assignment. In: Proceedings of CDOCS 2003. LNCS (LNAI), Springer, Heidelberg (2003) (fortcoming); Also available as TR"},{"key":"18_CR19","unstructured":"Tumer, K., Wolpert, D.: COllective INtelligence and Braess\u2019 paradox. In: Proceedings of the Sixteenth National Conference on Artificial Intelligence, Austin, August 2000, pp. 104\u2013109 (2000)"},{"key":"18_CR20","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-540-39857-8_38","volume-title":"Machine Learning: ECML 2003","author":"K. Tuyls","year":"2003","unstructured":"Tuyls, K., Heytens, D., Nowe, A., Manderick, B.: Extended replicator dynamics as a key to reinforcement learning in multi-agent systems. In: Lavra\u010d, N., Gamberger, D., Todorovski, L., Blockeel, H. (eds.) ECML 2003. LNCS (LNAI), vol.\u00a02837, pp. 421\u2013431. Springer, Heidelberg (2003)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Tuyls, K., Verbeeck, K., Lenaerts, T.: A selection-mutation model for Q-learning in multi-agent systems. In: AAMAS, The ACM International Conference Proceedings Series (2003)","DOI":"10.1145\/860575.860687"},{"key":"18_CR22","first-page":"279","volume":"8","author":"Watkins","year":"1992","unstructured":"Watkins, Dayan: Q-learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"18_CR23","volume-title":"Evolutionary Game Theory","author":"J. Weibull","year":"1995","unstructured":"Weibull, J.: Evolutionary Game Theory. The MIT Press, Cambridge (1995)"},{"issue":"2\/3","key":"18_CR24","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1142\/S0219525901000188","volume":"4","author":"D. Wolpert","year":"2001","unstructured":"Wolpert, D., Tumer, K.: Optimal payoff functions for members of collectives. Advances in Complex Systems\u00a04(2\/3), 265\u2013279 (2001)","journal-title":"Advances in Complex Systems"},{"key":"18_CR25","unstructured":"Wolpert, D.H., Tumer, K., Frank, J.: Using collective intelligence to route internet traffic. In: Advances in Neural Information Processing Systems-11, Denver, pp. 952\u2013958 (1998)"},{"key":"18_CR26","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1145\/301136.301167","volume-title":"Proceedings of the Third Annual Conference on Autonomous Agents (AGENTS 1999)","author":"D.H. Wolpert","year":"1999","unstructured":"Wolpert, D.H., Wheeler, K.R., Tumer, K.: General principles of learning-based multi-agent systems. In: Etzioni, O., M\u00fcller, J.P., Bradshaw, J.M. (eds.) Proceedings of the Third Annual Conference on Autonomous Agents (AGENTS 1999), May 1-5, pp. 77\u201383. ACM Press, New York (1999)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning: ECML 2004"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-30115-8_18.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T04:40:56Z","timestamp":1605760856000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-30115-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004]]},"ISBN":["9783540231059","9783540301158"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-30115-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2004]]}}}