{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T16:41:36Z","timestamp":1770482496221,"version":"3.49.0"},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540201212","type":"print"},{"value":"9783540398578","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2003]]},"DOI":"10.1007\/978-3-540-39857-8_18","type":"book-chapter","created":{"date-parts":[[2010,6,28]],"date-time":"2010-06-28T00:07:15Z","timestamp":1277683635000},"page":"181-192","source":"Crossref","is-referenced-by-count":8,"title":["COllective INtelligence with Sequences of Actions"],"prefix":"10.1007","author":[{"given":"Pieter Jan \u2019t","family":"Hoen","sequence":"first","affiliation":[]},{"given":"Sander M.","family":"Bohte","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"18_CR1","unstructured":"Barto, A., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Discrete-Event Systems journal (2003) (to appear)"},{"key":"18_CR2","unstructured":"Guestrin, C., Lagoudakis, M., Parr, R.: Coordinated reinforcement learning. In: Proceedings of the ICML 2002 The Nineteenth International Conference on Machine Learning (2002)"},{"key":"18_CR3","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1126\/science.162.3859.1243","volume":"162","author":"G. Hardin","year":"1968","unstructured":"Hardin, G.: The tragedy of the commons. Science\u00a0162, 1243\u20131248 (1968)","journal-title":"Science"},{"key":"18_CR4","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_CR5","volume-title":"Machine Learning","author":"T. Mitchell","year":"1997","unstructured":"Mitchell, T.: Machine Learning. McGraw-Hill, New York (1997)"},{"key":"18_CR6","unstructured":"Personal communication with A. Agogino"},{"key":"18_CR7","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/3-540-36755-1_25","volume-title":"Machine Learning: ECML 2002","author":"I. Menache","year":"2002","unstructured":"Menache, I., Mannor, S., Shimkin, N.: Q-cut - dynamic discovery of sub-goals in Reinforcement Learning. In: Elomaa, T., Mannila, H., Toivonen, H. (eds.) ECML 2002. LNCS (LNAI), vol.\u00a02430, pp. 295\u2013306. Springer, Heidelberg (2002)"},{"key":"18_CR8","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_CR9","unstructured":"Thrun, S.B.: Efficient exploration in reinforcement learning. Technical Report CMU-CS-92-102, Carnegie Mellon University, Pittsburgh, Pennsylvania (1992)"},{"key":"18_CR10","first-page":"378","volume-title":"Autonomous Agents & Multiagent Systems, part 1","author":"K. Tumer","year":"2002","unstructured":"Tumer, K., Agogino, A., Wolpert, D.: Learning sequences of actions in collectives of autonomous agents. In: Autonomous Agents & Multiagent Systems, part 1, pp. 378\u2013385. ACM Press, New York (2002)"},{"key":"18_CR11","unstructured":"Tumer, K., Wolpert, D.: COllective INtelligence and Braess paradox. In: Proceedings of the Sixteenth National Conference on Artificial Intelligence, Austin, August 2000, pp. 104\u2013109 (2000)"},{"key":"18_CR12","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_CR13","unstructured":"Weiss, G.: A multiagent framework for planning, reacting, and learning. Technical Report FKI-233-99, Institut f\u00fcr Informatik, Technische Universit\u00e4t M\u00fcnchen (1999)"},{"issue":"4es","key":"18_CR14","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1145\/242224.242242","volume":"28","author":"M.P. Wellman","year":"1996","unstructured":"Wellman, M.P.: The economic approach to artificial intelligence. ACM Computing Surveys\u00a028(4es), 14\u201315 (1996)","journal-title":"ACM Computing Surveys"},{"key":"18_CR15","volume-title":"Market-Based Control: A Paradigm for Distributed Resource Allocation","author":"M.P. Wellman","year":"1996","unstructured":"Wellman, M.P.: Market-oriented programming: Some early lessons. In: Clearwater, S. (ed.) Market-Based Control: A Paradigm for Distributed Resource Allocation, World Scientific, River Edge (1996)"},{"key":"18_CR16","unstructured":"Wiering, M.: Explorations in Efficient Reinforcement Learning. PhD thesis, University of Amsterdam (1999)"},{"key":"18_CR17","unstructured":"Wolpert, D., Tumer, K.: An introduction to COllective INtelligence. Technical Report NASA-ARC-IC-99-63, NASA Ames Research Center, 1999. A shorter version of this paper is to appear in: Bradshaw, J.M. (edi.) Handbook of Agent Technology, AAAI Press\/MIT Press (1999)"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Wolpert, D., Tumer, K.: Optimal payoff functions for members of collectives. Advances in Complex Systems (2001) (in press)","DOI":"10.1142\/S0219525901000188"},{"key":"18_CR19","unstructured":"Wolpert, D.H., Tumer, K., Frank, J.: Using collective intelligence to route internet traffic. In: Advances in Neural Information Processing Systems-11, December 1998, pp. 952\u2013958, Denver (1998)"},{"key":"18_CR20","unstructured":"Wolpert, D.H., Tumer, K., Frank, J.: Using collective intelligence to route internet traffic. In: Advances in Neural Information Processing Systems-11, pp. 952\u2013958, Denver (1998)"},{"key":"18_CR21","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), pp. 77\u201383. ACM Press, New York (1999)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning: ECML 2003"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-39857-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,14]],"date-time":"2019-03-14T23:53:05Z","timestamp":1552607585000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-39857-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540201212","9783540398578"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-39857-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2003]]}}}