{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T13:42:34Z","timestamp":1773236554614,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540330530","type":"print"},{"value":"9783540330592","type":"electronic"}],"license":[{"start":{"date-parts":[[2006,1,1]],"date-time":"2006-01-01T00:00:00Z","timestamp":1136073600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11691839_12","type":"book-chapter","created":{"date-parts":[[2006,3,6]],"date-time":"2006-03-06T07:31:37Z","timestamp":1141630297000},"page":"192-206","source":"Crossref","is-referenced-by-count":5,"title":["Multi-agent Relational Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Tom","family":"Croonenborghs","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karl","family":"Tuyls","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Ramon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maurice","family":"Bruynooghe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"12_CR1","first-page":"103","volume-title":"A Framework for Behavioral Cloning","author":"M. Bain","year":"1995","unstructured":"Bain, M., Sammut, C.: Machine Intelligence Agents. In: A Framework for Behavioral Cloning, pp. 103\u2013129. Oxford University Press, Oxford (1995)"},{"key":"12_CR2","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multi-agent systems. In: Proceedings of the 15th International Conference on Artificial Intelligence, pp. 746\u2013752 (1998)"},{"key":"12_CR3","unstructured":"Croonenborghs, T., Ramon, J., Bruynooghe, M.: Towards informed reinforcement learning. In: Tadepalli, P., Givan, R., Driessens, K. (eds.) Proceedings of the ICML 2004 Workshop on Relational Reinforcement Learning, Banff, Canada, July 2004, pp. 21\u201326 (2004)"},{"key":"12_CR4","unstructured":"Driessens, K.: Relational Reinforcement Learning. PhD thesis, Department of Computer Science, Katholieke Universiteit Leuven (2004), \n                  \n                    http:\/\/www.cs.kuleuven.be\/publicaties\/doctoraten\/cw\/CW200405.abs.html"},{"issue":"3","key":"12_CR5","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1023\/B:MACH.0000039779.47329.3a","volume":"57","author":"K. Driessens","year":"2004","unstructured":"Driessens, K., Dzeroski, S.: Integrating guidance into relational reinforcement learning. Machine Learning\u00a057(3), 271\u2013304 (2004)","journal-title":"Machine Learning"},{"key":"12_CR6","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/3-540-44795-4_9","volume-title":"Machine Learning: ECML 2001","author":"K. Driessens","year":"2001","unstructured":"Driessens, K., Ramon, J., Blockeel, H.: Speeding up relational reinforcement learning through the use of an incremental first order decision tree learner. In: Flach, P.A., De Raedt, L. (eds.) ECML 2001. LNCS (LNAI), vol.\u00a02167, pp. 97\u2013108. Springer, Heidelberg (2001)"},{"key":"12_CR7","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1007694015589","volume":"43","author":"S. D\u017eeroski","year":"2001","unstructured":"D\u017eeroski, S., De Raedt, L., Driessens, K.: Relational reinforcement learning. Machine Learning\u00a043, 7\u201352 (2001)","journal-title":"Machine Learning"},{"key":"12_CR8","unstructured":"Grenager, T., Powers, R., Shoham, Y.: Dispersion games: General definitions and some specific learning results. In: Eighteenth National Conference on Artificial Intelligence, Edmonton, Alberta, Canada, pp. 398\u2013403 (2002)"},{"key":"12_CR9","unstructured":"Hoen, P., Tuyls, K.: Engineering multi-agent reinforcement learning using evolutionary dynamics. In: Proceedings of the 15th European Conference on Machine Learning (2004)"},{"key":"12_CR10","first-page":"407","volume-title":"ICML 2000: Proceedings of the Seventeenth International Conference on Machine Learning","author":"J. Hu","year":"2000","unstructured":"Hu, J., Wellman, M.P.: Experimental results on Q-learning for general-sum stochastic games. In: ICML 2000: Proceedings of the Seventeenth International Conference on Machine Learning, pp. 407\u2013414. Morgan Kaufmann Publishers Inc., San Francisco (2000)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Kaelbling, L., Littman, M., Moore, A.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research (1996)","DOI":"10.1613\/jair.301"},{"key":"12_CR12","volume-title":"Proceedings of the 14th International Conference on inductive logic programming","author":"K. Kersting","year":"2004","unstructured":"Kersting, K., De Raedt, L.: Logical Markov Decision Programs and the Convergence of Logical TD(\u00eb). In: Proceedings of the 14th International Conference on inductive logic programming. Springer, Heidelberg (to appear, 2004)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Littman, M.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the Eleventh International Conference on Machine Learning, pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"12_CR14","first-page":"76","volume-title":"ICML 2004: Proceedings of the Twenty-First International Conference on Machine Learning","author":"E.F. Morales","year":"2004","unstructured":"Morales, E.F., Sammut, C.: Learning to fly by combining reinforcement learning with behavioural cloning. In: ICML 2004: Proceedings of the Twenty-First International Conference on Machine Learning, p. 76. ACM Press, New York (2004)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Now\u00e9, A., Parent, J., Verbeeck, K.: Social agents playing a periodical policy. In: Proceedings of the 12th European Conference on Machine Learning, Freiburg, pp. 382\u2013393 (2001)","DOI":"10.1007\/3-540-44795-4_33"},{"key":"12_CR16","unstructured":"Ramon, J.: On the convergence of reinforcement learning using a decision tree learner. In: Proceedings of ICML-2005 Workshop on Rich Representation for Reinforcement Learning, Bonn, Germany (2005), \n                  \n                    http:\/\/www.cs.kuleuven.ac.be\/cgi-bin-dtai\/publ_info.pl?id=41743"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Sen, S., Airiau, S., Mukherjee, R.: Towards a Pareto-optimal solution in generalsum games. In: The Proceedings of the Second Intenational Joint Conference on Autonomous Agents and Multiagent Systems, Melbourne, Australia, July 2003, pp. 153\u2013160 (2003)","DOI":"10.1145\/860575.860600"},{"key":"12_CR18","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4151.001.0001","volume-title":"Layered learning in multi-agent systems","author":"P. Stone","year":"2000","unstructured":"Stone, P.: Layered learning in multi-agent systems. MIT Press, Cambridge (2000)"},{"key":"12_CR19","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":"12_CR20","unstructured":"Tadepalli, P., Givan, R., Driessens, K.: Relational reinfocement learning: An overview. In: Proceedings of the ICML 2004 Workshop on Relational Reinfocement Learning (2004)"},{"key":"12_CR21","unstructured":"Tumer, K., Wolpert, D.: COllective INtelligence and Braess Paradox. In: Proceedings of the Sixteenth National Conference on Artificial Intelligence, pp. 104\u2013109 (2000)"},{"key":"12_CR22","unstructured":"Tuyls, K., Croonenborghs, T., Ramon, J., Goetschalckx, R., Bruynooghe, M.: Multi-agent relational reinforcement learning. In: Tuyls, K., Verbeeck, K., Hoen, P.J.\u2019., Sen, S. (eds.) Proceedings of the First International Workshop on Learning and Adaptation in Multi Agent Systems, Utrecht, The Netherlands, July 25-26, pp. 123\u2013132 (2005)"},{"key":"12_CR23","volume-title":"The second International Joint Conference on Autonomous Agents and Multi-Agent Systems","author":"K. Tuyls","year":"2003","unstructured":"Tuyls, K., Verbeeck, K., Lenaerts, T.: A selection-mutation model for Q-learning in Multi-Agent Systems. In: The second International Joint Conference on Autonomous Agents and Multi-Agent Systems, Melbourne, Australia. ACM Press, New York (2003)"},{"key":"12_CR24","unstructured":"van Otterlo, M.: A characterization of sapient agents. In: International Conference Integration of Knowledge Intensive Multi-Agent Systems (KIMAS 2003), Boston, Massachusetts (2003)"}],"container-title":["Lecture Notes in Computer Science","Learning and Adaption in Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11691839_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,1,8]],"date-time":"2020-01-08T13:18:26Z","timestamp":1578489506000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11691839_12"}},"subtitle":["Explorations in Multi-state Coordination Tasks"],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540330530","9783540330592"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/11691839_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006]]}}}