{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:48:03Z","timestamp":1725558483878},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540201212"},{"type":"electronic","value":"9783540398578"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2003]]},"DOI":"10.1007\/978-3-540-39857-8_27","type":"book-chapter","created":{"date-parts":[[2010,6,28]],"date-time":"2010-06-28T04:07:15Z","timestamp":1277698035000},"page":"289-300","source":"Crossref","is-referenced-by-count":6,"title":["Self-evaluated Learning Agent in Multiple State Games"],"prefix":"10.1007","author":[{"given":"Koichi","family":"Moriyama","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masayuki","family":"Numao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"27_CR1","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M. Bowling","year":"2002","unstructured":"Bowling, M., Veloso, M.: Multiagent learning using a variable learning rate. Artificial Intelligence\u00a0136, 215\u2013250 (2002)","journal-title":"Artificial Intelligence"},{"key":"27_CR2","unstructured":"Claus, C., Boutilier, C.: The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems. In: Proc. 15th National Conference on Artificial Intelligence, AAAI 1998, Madison, Wisconsin, U.S.A., pp. 746\u2013752 (1998)"},{"key":"27_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":"27_CR4","unstructured":"Hu, J., Wellman, M.P.: Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm. In: Proc. 15th International Conference on Machine Learning, ICML 1998, Madison, Wisconsin, U.S.A., pp. 242\u2013250 (1998)"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Ishida, T., Yokoi, H., Kakazu, Y.: Self-Organized Norms of Behavior under Interactions of Selfish Agents. In: Proc. 1999 IEEE International Conference on Systems, Man, and Cybernetics, Tokyo, Japan (1999)","DOI":"10.1109\/ICSMC.1999.823192"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proc. 11th International Conference on Machine Learning, ML 1994, New Brunswick, New Jersey, U.S.A., pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"27_CR7","unstructured":"Mikami, S., Kakazu, Y.: Co-operation of Multiple Agents Through Filtering Payoff. In: Proc. 1st European Workshop on Reinforcement Learning, EWRL-1, Brussels, Belgium, pp. 97\u2013107 (1994)"},{"key":"27_CR8","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/3-540-59286-5_77","volume-title":"Machine Learning: ECML-95","author":"S. Mikami","year":"1995","unstructured":"Mikami, S., Kakazu, Y., Fogarty, T.C.: Co-operative Reinforcement Learning By Payoff Filters. In: Lavra\u010d, N., Wrobel, S. (eds.) ECML 1995. LNCS (LNAI), vol.\u00a0912, pp. 319\u2013322. Springer, Heidelberg (1995)"},{"key":"27_CR9","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/3-540-44533-1_35","volume-title":"PRICAI 2000 Topics in Artificial Intelligence","author":"K. Moriyama","year":"2000","unstructured":"Moriyama, K., Numao, M.: Constructing an Autonomous Agent with an Interdependent Heuristics. In: Mizoguchi, R., Slaney, J.K. (eds.) PRICAI 2000. LNCS (LNAI), vol.\u00a01886, pp. 329\u2013339. Springer, Heidelberg (2000)"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Moriyama, K., Numao, M.: Construction of a Learning Agent Handling Its Rewards According to Environmental Situations. In: Proc. 1st International Joint Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2002, Bologna, Italy, pp. 1262\u20131263 (2002)","DOI":"10.1145\/545056.545110"},{"key":"27_CR11","unstructured":"Moriyama, K., Numao, M.: Generating Self-Evaluations to Learn Appropriate Actions in Various Games. Technical Report TR03-0002, Department of Computer Science, Tokyo Institute of Technology (2003)"},{"key":"27_CR12","unstructured":"Mundhe, M., Sen, S.: Evolving agent societies that avoid social dilemmas. In: Proc. Genetic and Evolutionary Computation Conference, GECCO 2000, Las Vegas, Nevada, U.S.A., pp. 809\u2013816 (2000)"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Nagayuki, Y., Ishii, S., Doya, K.: Multi-Agent Reinforcement Learning: An Approach Based on the Other Agent\u2019s Internal Model. In: Proc. 4th International Conference on MultiAgent Systems, ICMAS 2000, Boston, Massachusetts, U.S.A., pp. 215\u2013221 (2000)","DOI":"10.1109\/ICMAS.2000.858456"},{"key":"27_CR14","volume-title":"Prisoner\u2019s Dilemma","author":"W. Poundstone","year":"1992","unstructured":"Poundstone, W.: Prisoner\u2019s Dilemma. Doubleday, New York (1992)"},{"key":"27_CR15","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/S0896-6273(02)00755-9","volume":"35","author":"J.K. Rilling","year":"2002","unstructured":"Rilling, J.K., Gutman, D.A., Zeh, T.R., Pagnoni, G., Berns, G.S., Kilts, C.D.: A Neural Basis for Social Cooperation. Neuron\u00a035, 395\u2013405 (2002)","journal-title":"Neuron"},{"key":"27_CR16","unstructured":"Sakaguchi, Y., Takano, M.: Learning to Switch Behaviors for Different Environments: A Computational Model for Incremental Modular Learning. In: Proc. 2001 International Symposium on Nonlinear Theory and its Applications, NOLTA 2001, Zao, Miyagi, Japan, pp. 383\u2013386 (2001)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J., Zhao, J., Schraudolph, N.N.: Reinforcement Learning with Self- Modifying Policies. In: [19], pp. 293\u2013309 (1997)","DOI":"10.1007\/978-1-4615-5529-2_12"},{"key":"27_CR18","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"volume-title":"Learning to Learn","year":"1997","key":"27_CR19","unstructured":"Thrun, S., Pratt, L. (eds.): Learning to Learn. Kluwer Academic Publishers, Norwell (1997)"},{"key":"27_CR20","first-page":"279","volume":"8","author":"C.J.C.H. Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Technical Note: Q-learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"27_CR21","volume-title":"Evolutionary Game Theory","author":"J.W. Weibull","year":"1995","unstructured":"Weibull, J.W.: Evolutionary Game Theory. MIT Press, Cambridge (1995)"},{"key":"27_CR22","first-page":"69","volume":"23","author":"G. Widmer","year":"1996","unstructured":"Widmer, G., Kubat, M.: Learning in the Presence of Concept Drift and Hidden Contexts. Machine Learning\u00a023, 69\u2013101 (1996)","journal-title":"Machine Learning"},{"key":"27_CR23","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1080\/08839510290030273","volume":"16","author":"D.H. Wolpert","year":"2002","unstructured":"Wolpert, D.H., Tumer, K.: Collective Intelligence, Data Routing and Braess\u2019 Paradox. Journal of Artificial Intelligence Research\u00a016, 359\u2013387 (2002)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, J., Schmidhuber, J.: Solving a Complex Prisoner\u2019s Dilemma with Self-Modifying Policies. In: From Animals to Animats 5: Proc. 5th International Conference on Simulation of Adaptive Behavior, Zurich, Switzerland, pp. 177\u2013182 (1998)","DOI":"10.7551\/mitpress\/3119.003.0028"}],"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_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T21:02:21Z","timestamp":1711573341000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-39857-8_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540201212","9783540398578"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-39857-8_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2003]]}}}