{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T17:00:40Z","timestamp":1725469240082},"publisher-location":"Berlin, Heidelberg","reference-count":26,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540368434"},{"type":"electronic","value":"9783540368465"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11805816_5","type":"book-chapter","created":{"date-parts":[[2006,8,25]],"date-time":"2006-08-25T15:30:30Z","timestamp":1156519830000},"page":"32-46","source":"Crossref","is-referenced-by-count":1,"title":["Multi-agent Case-Based Reasoning for Cooperative Reinforcement Learners"],"prefix":"10.1007","author":[{"given":"Thomas","family":"Gabel","sequence":"first","affiliation":[]},{"given":"Martin","family":"Riedmiller","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"5_CR1","volume-title":"Neuro Dynamic Programming","author":"D. Bertsekas","year":"1996","unstructured":"Bertsekas, D., Tsitsiklis, J.: Neuro Dynamic Programming. Athena Scientific, Belmont (1996)"},{"key":"5_CR2","first-page":"699","volume-title":"Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI 2003)","author":"M. Bowling","year":"2003","unstructured":"Bowling, M., Veloso, M.: Simultaneous Adversarial Multi-Robot Learning. In: Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI 2003), Acapulco, Mexico, pp. 699\u2013704. Morgan Kaufmann, San Francisco (2003)"},{"key":"5_CR3","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/11536406_1","volume-title":"Case-Based Reasoning Research and Development","author":"D. Bridge","year":"2005","unstructured":"Bridge, D.: The Virtue of Reward: Performance, Reinforcement and Discovery in Case-Based Reasoning. In: Mu\u00f1oz-\u00c1vila, H., Ricci, F. (eds.) ICCBR 2005. LNCS (LNAI), vol.\u00a03620, p. 1. Springer, Heidelberg (2005)"},{"key":"5_CR4","volume-title":"Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI 1998)","author":"C. Claus","year":"1998","unstructured":"Claus, C., Boutilier, C.: The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI 1998). AAAI Press, Menlo Park (1998)"},{"key":"5_CR5","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/11536406_18","volume-title":"Case-Based Reasoning Research and Development","author":"T. Gabel","year":"2005","unstructured":"Gabel, T., Riedmiller, M.: CBR for State Value Function Approximation in Reinforcement Learning. In: Mu\u00f1oz-\u00c1vila, H., Ricci, F. (eds.) ICCBR 2005. LNCS (LNAI), vol.\u00a03620, pp. 206\u2013221. Springer, Heidelberg (2005)"},{"unstructured":"Gabel, T., Riedmiller, M.: Reducing Policy Degradation in Neuro-Dynamic Programming. In: Proceedings of ESANN 2006, Bruges, Belgium (to appear, 2006)","key":"5_CR6"},{"key":"5_CR7","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1162\/jmlr.2003.4.6.1039","volume":"4","author":"J. Hu","year":"2003","unstructured":"Hu, J., Wellman, M.: Nash Q-Learning for General-Sum Stochastic Games. Journal of Machine Learning Research\u00a04, 1039\u20131069 (2003)","journal-title":"Journal of Machine Learning Research"},{"key":"5_CR8","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1007\/978-3-540-28631-8_47","volume-title":"Advances in Case-Based Reasoning","author":"J. Kim","year":"2004","unstructured":"Kim, J., Seong, D., Jung, S., Park, J.: Integrated CBR Framework for Quality Designing and Scheduling in Steel Industry. In: Funk, P., Gonz\u00e1lez Calero, P.A. (eds.) ECCBR 2004. LNCS (LNAI), vol.\u00a03155, pp. 645\u2013658. Springer, Heidelberg (2004)"},{"key":"5_CR9","first-page":"1514","volume-title":"Proceedings of AAMAS 2004","author":"M. Lauer","year":"2004","unstructured":"Lauer, M., Riedmiller, M.: Reinforcement Learning for Stochastic Cooperative Multi-Agent Systems. In: AAMAS 2004, pp. 1514\u20131515. ACM Press, New York (2004)"},{"key":"5_CR10","first-page":"106","volume-title":"FLAIRS Conference","author":"D. Leake","year":"2002","unstructured":"Leake, D., Sooriamurthi, R.: Managing Multiple Case Bases: Dimensions and Issues. In: FLAIRS Conference, Pensacola Beach, pp. 106\u2013110. AAAI Press, Menlo Park (2002)"},{"key":"5_CR11","first-page":"322","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001)","author":"M. Littman","year":"2001","unstructured":"Littman, M.: Friend-or-Foe Q-learning in General-Sum Games. In: Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001), Williamstown, USA, pp. 322\u2013328. Morgan Kaufman, San Francisco (2001)"},{"issue":"4","key":"5_CR12","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1109\/TEVC.2004.823466","volume":"8","author":"S. Louis","year":"2004","unstructured":"Louis, S., McDonnell, J.: Learning with Case-Injected Genetic Algorithms. IEEE Trans. Evolutionary Computation\u00a08(4), 316\u2013328 (2004)","journal-title":"IEEE Trans. Evolutionary Computation"},{"key":"5_CR13","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1007\/978-3-540-28631-8_21","volume-title":"Advances in Case-Based Reasoning","author":"L. Macedo","year":"2004","unstructured":"Macedo, L., Cardoso, A.: Using CBR in the Exploration of Unknown Environments with an Autonomous Agent. In: Funk, P., Gonz\u00e1lez Calero, P.A. (eds.) ECCBR 2004. LNCS (LNAI), vol.\u00a03155, pp. 272\u2013286. Springer, Heidelberg (2004)"},{"key":"5_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/3-540-45006-8_31","volume-title":"Case-Based Reasoning Research and Development","author":"S. Ontanon","year":"2003","unstructured":"Ontanon, S., Plaza, E.: Collaborative Case Retention Strategies for CBR Agents. In: Ashley, K.D., Bridge, D.G. (eds.) ICCBR 2003. LNCS, vol.\u00a02689, pp. 392\u2013406. Springer, Heidelberg (2003)"},{"key":"5_CR15","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/11536406_30","volume-title":"Case-Based Reasoning Research and Development","author":"S. Ontanon","year":"2005","unstructured":"Ontanon, S., Plaza, E.: Cooperative Reuse for Compositional Cases in Multi-agent Systems. In: Mu\u00f1oz-\u00c1vila, H., Ricci, F. (eds.) ICCBR 2005. LNCS (LNAI), vol.\u00a03620, pp. 382\u2013396. Springer, Heidelberg (2005)"},{"key":"5_CR16","volume-title":"Scheduling. Theory, Algorithms, and Systems","author":"M. Pinedo","year":"2002","unstructured":"Pinedo, M.: Scheduling. Theory, Algorithms, and Systems. Prentice Hall, Englewood Cliffs (2002)"},{"key":"5_CR17","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1007\/11536406_31","volume-title":"Case-Based Reasoning Research and Development","author":"J. Powell","year":"2005","unstructured":"Powell, J., Hauff, B., Hastings, J.: Evaluating the Effectiveness of Exploration and Accumulated Experience in Automatic Case Elicitation. In: Mu\u00f1oz-\u00c1vila, H., Ricci, F. (eds.) ICCBR 2005. LNCS (LNAI), vol.\u00a03620, pp. 397\u2013407. Springer, Heidelberg (2005)"},{"key":"5_CR18","volume-title":"Adaptivity and Learning","author":"M. Riedmiller","year":"2003","unstructured":"Riedmiller, M., Merke, A.: Using Machine Learning Techniques in Complex Multi-Agent Domains. In: Stamatescu, I., Menzel, W., Richter, M., Ratsch, U. (eds.) Adaptivity and Learning. Springer, Heidelberg (2003)"},{"unstructured":"Riedmiller, S., Riedmiller, M.: A Neural Reinforcement Learning Approach to Learn Local Dispatching Policies in Production Scheduling. In: Proceedings of ICJAI 1999, Stockholm, Sweden, pp. 764\u2013771 (1999)","key":"5_CR19"},{"issue":"2","key":"5_CR20","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1177\/105971239700600201","volume":"6","author":"J. Santamaria","year":"1998","unstructured":"Santamaria, J., Sutton, R., Ram, A.: Experiments with RL in Problems with Continuous State and Action Spaces. Adaptive Behavior\u00a06(2), 163\u2013217 (1998)","journal-title":"Adaptive Behavior"},{"doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning. An Introduction. MIT Press\/A Bradford Book, Cambridge (1998)","key":"5_CR21","DOI":"10.1109\/TNN.1998.712192"},{"key":"5_CR22","first-page":"1254","volume-title":"Proceedings of AAMAS 2004","author":"D. Szer","year":"2004","unstructured":"Szer, D., Charpillet, F.: Coordination through Mutual Notification in Cooperative Multiagent Reinforcement Learning. In: Proceedings of AAMAS 2004, New York, USA, pp. 1254\u20131255. IEEE Computer Society, Los Alamitos (2004)"},{"key":"5_CR23","volume-title":"Proceedings of NIPS 2003","author":"G. Tesauro","year":"2003","unstructured":"Tesauro, G.: Extending Q-Learning to General Adaptive Multi-Agent Systems. In: Proceedings of NIPS 2003, Vancouver and Whistler, Canada. MIT Press, Cambridge (2003)"},{"key":"5_CR24","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1007\/11536406_43","volume-title":"Case-Based Reasoning Research and Development","author":"P. Tinkler","year":"2005","unstructured":"Tinkler, P., Fox, J., Green, C., Rome, D., Casey, K., Furmanski, C.: Analogical and Case-Based Reasoning for Predicting Satellite Task Schedulability. In: Mu\u00f1oz-\u00c1vila, H., Ricci, F. (eds.) ICCBR 2005. LNCS (LNAI), vol.\u00a03620, pp. 566\u2013578. Springer, Heidelberg (2005)"},{"unstructured":"Uther, W., Veloso, M.: Adversarial Reinforcement Learning. Technical Report CMU-CS-03-107, School of Computer Science, Carnegie Mellon University (2003)","key":"5_CR25"},{"key":"5_CR26","first-page":"279","volume":"8","author":"C. Watkins","year":"1992","unstructured":"Watkins, C., Dayan, P.: Q-Learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"}],"container-title":["Lecture Notes in Computer Science","Advances in Case-Based Reasoning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11805816_5.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T20:13:03Z","timestamp":1605643983000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11805816_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540368434","9783540368465"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/11805816_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}