{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T15:29:58Z","timestamp":1725550198143},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642116872"},{"type":"electronic","value":"9783642116889"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-11688-9_2","type":"book-chapter","created":{"date-parts":[[2010,3,22]],"date-time":"2010-03-22T05:34:40Z","timestamp":1269236080000},"page":"45-63","source":"Crossref","is-referenced-by-count":3,"title":["Learning with Whom to Communicate Using Relational Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Marc","family":"Ponsen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Croonenborghs","sequence":"additional","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":"Kurt","family":"Driessens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaap","family":"van den Herik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Postma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"2_CR1","volume-title":"Dynamic Programming","author":"R. Bellman","year":"1957","unstructured":"Bellman, R.: Dynamic Programming. Princeton University Press, Princeton (1957)"},{"key":"2_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":"2_CR3","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1007\/11691839_12","volume-title":"Learning and Adaption in Multi-Agent Systems","author":"T. Croonenborghs","year":"2006","unstructured":"Croonenborghs, T., Tuyls, K., Ramon, J., Bruynooghe, M.: Multi-agent relational reinforcement learning. In: Tuyls, K., \u2019t Hoen, P.J., Verbeeck, K., Sen, S. (eds.) LAMAS 2005. LNCS (LNAI), vol.\u00a03898, pp. 192\u2013206. Springer, Heidelberg (2006), http:\/\/www.cs.kuleuven.ac.be\/cgi-bin-dtai\/publ_info.pl?id=41977"},{"key":"2_CR4","unstructured":"Driessens, K.: Relational reinforcement learning. Ph.D. thesis, Department of Computer Science, Katholieke Universiteit Leuven (2004), http:\/\/www.cs.kuleuven.be\/publicaties\/doctoraten\/cw\/CW2004_05.abs.html"},{"key":"2_CR5","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":"2_CR6","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":"2_CR7","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1145\/1082473.1082743","volume-title":"AAMAS 2005: Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems","author":"A. Finzi","year":"2005","unstructured":"Finzi, A., Lukasiewicz, T.: Game theoretic golog under partial observability. In: AAMAS 2005: Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems, pp. 1301\u20131302. ACM, New York (2005), http:\/\/doi.acm.org\/10.1145\/1082473.1082743"},{"key":"2_CR8","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1007\/978-3-540-30200-1_12","volume-title":"Computational Logic in Multi-Agent Systems","author":"A. Guerra-Hern\u00e1ndez","year":"2004","unstructured":"Guerra-Hern\u00e1ndez, A., Fallah-Seghrouchni, A.E., Soldano, H.: Learning in BDI multi-agent systems. In: Dix, J., Leite, J. (eds.) CLIMA 2004. LNCS (LNAI), vol.\u00a03259, pp. 218\u2013233. Springer, Heidelberg (2004)"},{"key":"2_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":"2_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":"2_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"},{"issue":"2","key":"2_CR12","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1142\/S0218213002000873","volume":"11","author":"I.A. Letia","year":"2002","unstructured":"Letia, I.A., Precup, D.: Developing collaborative golog agents by reinforcement learning. International Journal on Artificial Intelligence Tools\u00a011(2), 233\u2013246 (2002)","journal-title":"International Journal on Artificial Intelligence Tools"},{"key":"2_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":"2_CR14","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1016\/0743-1066(94)90035-3","volume":"19,20","author":"S. Muggleton","year":"1994","unstructured":"Muggleton, S., De Raedt, L.: Inductive logic programming: Theory and methods. Journal of Logic Programming\u00a019,20, 629\u2013679 (1994)","journal-title":"Journal of Logic Programming"},{"key":"2_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":"2_CR16","volume-title":"International Conference Integration of Knowledge Intensive Multi-Agent Systems (KIMAS 2003)","author":"M. Otterlo van","year":"2003","unstructured":"van Otterlo, M.: A characterization of sapient agents. In: International Conference Integration of Knowledge Intensive Multi-Agent Systems (KIMAS 2003), Boston, Massachusetts (2003)"},{"issue":"3","key":"2_CR17","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s10458-005-2631-2","volume":"11","author":"L. Panait","year":"2005","unstructured":"Panait, L., Luke, S.: Cooperative multi-agent learning: The state of the art. Autonomous Agents and Multi-Agent Systems\u00a011(3), 387\u2013434 (2005)","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"2_CR18","first-page":"423","volume":"9","author":"L. Panait","year":"2008","unstructured":"Panait, L., Tuyls, K., Luke, S.: Theoretical advantages of lenient learners: An evolutionary game theoretic perspective. Journal of Machine Learning Research\u00a09, 423\u2013457 (2008)","journal-title":"Journal of Machine Learning Research"},{"key":"2_CR19","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes: Discrete stochastic dynamic programming","author":"M. Puterman","year":"1994","unstructured":"Puterman, M.: Markov decision processes: Discrete stochastic dynamic programming. John Wiley and Sons, New York (1994)"},{"key":"2_CR20","unstructured":"Rummery, G.A., Niranjan, M.: On-line Q-learning using connectionist systems. Tech. rep., Cambridge University Engineering Department (1994)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Sen, S., Airiau, S., Mukherjee, R.: Towards a Pareto-optimal solution in general-sum 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":"2_CR22","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":"2_CR23","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":"2_CR24","volume-title":"Reinforcement Learning: An Introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)"},{"key":"2_CR25","unstructured":"Tadepalli, P., Givan, R., Driessens, K.: Relational reinforcement learning: An overview. In: Proceedings of the ICML 2004 Workshop on Relational Reinforcement Learning (2004)"},{"key":"2_CR26","unstructured":"Tumer, K., Wolpert, D.: COllective INtelligence and Braess\u2019 Paradox. In: Proceedings of the Sixteenth National Conference on Artificial Intelligence, pp. 104\u2013109 (2000)"},{"key":"2_CR27","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. ACM Press, Melbourne (2003)"},{"key":"2_CR28","unstructured":"van Otterlo, M.: The logic of adaptive behavior: Knowledge representation and algorithms for the Markov decision process framework in first-order domains. Ph.D. thesis, Department of Computer Science, University of Twente, Enschede, The Netherlands, p. 512 (May 2008)"},{"key":"2_CR29","unstructured":"Watkins, C.: Learning with delayed rewards. Ph.D. thesis, Cambridge University (1989)"},{"key":"2_CR30","unstructured":"Wiering, M.: Explorations in efficient reinforcement learning. Ph.D. thesis, Universiteit van Amsterdam (1999)"}],"container-title":["Studies in Computational Intelligence","Interactive Collaborative Information Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-11688-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,27]],"date-time":"2019-05-27T11:27:36Z","timestamp":1558956456000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-11688-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642116872","9783642116889"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-11688-9_2","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"type":"print","value":"1860-949X"},{"type":"electronic","value":"1860-9503"}],"subject":[],"published":{"date-parts":[[2010]]}}}