{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T21:02:10Z","timestamp":1725483730029},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540679110"},{"type":"electronic","value":"9783540445944"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2000]]},"DOI":"10.1007\/3-540-44594-3_5","type":"book-chapter","created":{"date-parts":[[2007,5,1]],"date-time":"2007-05-01T05:41:03Z","timestamp":1177998063000},"page":"61-75","source":"Crossref","is-referenced-by-count":9,"title":["Rationality Assumptions and Optimality of Co-learning"],"prefix":"10.1007","author":[{"given":"Ron","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dehu","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2001,7,13]]},"reference":[{"key":"5_CR1","volume-title":"Dynamic Programming","author":"R. Bellman","year":"1957","unstructured":"R. Bellman, (1957). Dynamic Programming. Princeton University Press, Princeton, NJ."},{"key":"5_CR2","volume-title":"Neuro-Dynamic Programming","author":"D. Bertsekas","year":"1996","unstructured":"D. Bertsekas and J. Tsitsiklis, (1996). Neuro-Dynamic Programming. Athena Scientific, Belmont, MA."},{"key":"5_CR3","volume-title":"Proceedings of A AAI\u2019 98","author":"C. Claus","year":"1998","unstructured":"C. Claus and C. Boutilier, (1998). The dynamics of reinforcement learning in cooperative multiagent systems. Proceedings of A AAI\u2019 98. AAAI Press, San Mateo, CA."},{"key":"5_CR4","volume-title":"The Theory of Learning in Games","author":"D. Fudenberg","year":"1998","unstructured":"D. Fudenberg and D. Levine, (1998). The Theory of Learning in Games. MIT Press, Cambridge, MA."},{"key":"5_CR5","unstructured":"T. Haynes and S. Sen, (1996). Co-adaptation in a team. International Journal of Computational Intelligence and Organizations."},{"key":"5_CR6","first-page":"242","volume-title":"Proceedings of International Conference on Machine Learning","author":"J. Hu","year":"1998","unstructured":"J. Hu and M. Wellman, (1998 a). Multiagent reinforcement learning: theore-tical framework and an algorithm. Proceedings of International Conference on Machine Learning, 242\u2013250. Morgan Kaufmann, San Francisco, CA."},{"key":"5_CR7","volume-title":"Second International Conference on Autonomous Agents","author":"J. Hu","year":"1998","unstructured":"J. Hu and M. Wellman, (1998 b). Online learning about other agents in a dynamic multiagent system. Second International Conference on Autonomous Agents. ACM Press, New York."},{"key":"5_CR8","first-page":"157","volume-title":"Proc. of the 11th International conference on Machine Learning","author":"M. Littman","year":"1994","unstructured":"M. Littman, (1994). Markov games as a framework for multi-agent reinfocement learning. Proc. of the 11th International conference on Machine Learning, 157\u2013163. Morgan Kaufmann, San Francisco, CA."},{"key":"5_CR9","volume-title":"A Course on Game Theory","author":"M. Osborne","year":"1994","unstructured":"M. Osborne and A. Rubinstein, (1994). A Course on Game Theory. MIT Press, Cambridge, MA."},{"key":"5_CR10","unstructured":"R. Salustowicz, M. Wiering, and J. Schmidhuber, (1998). Learning team strategies: soccer case studies. Machine Learning. 1998"},{"key":"5_CR11","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1080\/095281398146798","volume":"10","author":"S. Sen","year":"1998","unstructured":"S. Sen and M. Sekaran, (1998). Individual learning of coordination knowledge. Journal of Experimental and Theoretical Artificial Intelligence, 10, 333\u2013356.","journal-title":"Journal of Experimental and Theoretical Artificial Intelligence"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Y. Shoham and M. Tennenholtz, (1994). Co-learning and the evolution of social activity. Technical Report STAN-CS-TR-94-1511, Stanford University.","DOI":"10.21236\/ADA325130"},{"key":"5_CR13","volume-title":"Advances in Neural Information Processing Systems 7","author":"S. Singh","year":"1994","unstructured":"S. Singh, T. Jaakkola, and M. Jordan, (1994). Reinforcement learning with soft state aggregation. In: S.J. Hanson J. Cowan and C. L. Giles, eds. Advances in Neural Information Processing Systems 7. Morgan Kaufmann, San Mateo, CA."},{"issue":"4\u20135","key":"5_CR14","first-page":"127","volume":"12","author":"R. Sun","year":"1999","unstructured":"R. Sun and T. Peterson, (1999). Multi-agent reinforcement learning: weighting and partitioning. Neural Networks, Vol. 12, No. 4\u20135. pp. 127\u2013153.","journal-title":"Neural Networks"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"R. Sun and C. Sessions, (1999). Bidding in reinforcement learning: a paradigm for multi-agent systems. Proc. of The Third International Conference on Autonomous Agents (AGENTS\u201999), Seattle, WA.","DOI":"10.1145\/301136.301226"},{"key":"5_CR16","volume-title":"Proceedings of Machine Learning Conference","author":"M. Tan","year":"1993","unstructured":"M. Tan, (1993). Multi-agent reinforcement learning: independent vs. cooperative agents. Proceedings of Machine Learning Conference. Morgan Kaufmann, San Francisco, CA."},{"key":"5_CR17","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0921-8890(95)00005-Z","volume":"15","author":"C. Tham","year":"1995","unstructured":"C. Tham, (1995). Reinforcement learning of multiple tasks using a hierarchical CMAC architecture. Robotics and Autonomous Systems. 15, 247\u2013274.","journal-title":"Robotics and Autonomous Systems"},{"issue":"3","key":"5_CR18","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1080\/095281398146770","volume":"10","author":"M. Vidal","year":"1998","unstructured":"M. Vidal and E.H. Durfee, (1998). Learning nested models in an information economy. Journal of Experimental and Theoretical Artificial Intelligence, 10(3), 291\u2013308.","journal-title":"Journal of Experimental and Theoretical Artificial Intelligence"},{"key":"5_CR19","series-title":"Ph.D Thesis","volume-title":"Learning with Delayed Rewards","author":"C. Watkins","year":"1989","unstructured":"C. Watkins, (1989). Learning with Delayed Rewards. Ph.D Thesis, Cambridge University, Cambridge, UK."},{"key":"5_CR20","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/0921-8890(95)00018-B","volume":"15","author":"G. Weiss","year":"1995","unstructured":"G. Weiss, (1995). Distributed reinforcement learning. Robotics and Autonomous Systems, 15, 135\u2013142.","journal-title":"Robotics and Autonomous Systems"}],"container-title":["Lecture Notes in Computer Science","Design and Applications of Intelligent Agents"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-44594-3_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,2,16]],"date-time":"2019-02-16T07:17:42Z","timestamp":1550301462000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-44594-3_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2000]]},"ISBN":["9783540679110","9783540445944"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/3-540-44594-3_5","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2000]]}}}