{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:26:24Z","timestamp":1753921584640},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540415978"},{"type":"electronic","value":"9783540445654"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2000]]},"DOI":"10.1007\/3-540-44565-x_13","type":"book-chapter","created":{"date-parts":[[2007,8,11]],"date-time":"2007-08-11T09:48:14Z","timestamp":1186825694000},"page":"288-307","source":"Crossref","is-referenced-by-count":11,"title":["Pricing in Agent Economies Using Neural Networks and Multi-agent Q-Learning"],"prefix":"10.1007","author":[{"given":"Gerald","family":"Tesauro","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2001,12,7]]},"reference":[{"key":"13_CR1","unstructured":"R. H. Crites and A. G. Barto, (1996). \u201cImproving elevator performance using reinforcement learning.\u201d In: D. Touretzky et al., eds., Advances in Neural Information Processing Systems 8, 1017\u20131023, MIT Press."},{"key":"13_CR2","unstructured":"A. Greenwald and J. O. Kephart, (1999). \u201cShopbots and pricebots.\u201d Proceedings of IJCAI-99, 506\u2013511."},{"key":"13_CR3","unstructured":"J. Hu and M. P. Wellman, (1996). \u201cSelf-fulfilling bias in multiagent learning.\u201d Proceedings of ICMAS-96, AAAI Press."},{"key":"13_CR4","unstructured":"J. Hu and M. P. Wellman, (1998). \u201cMultiagent reinforcement learning: theoretical framework and an algorithm.\u201d Proceedings of ICML-98, Morgan Kaufmann."},{"key":"13_CR5","unstructured":"J. O. Kephart, J. E. Hanson and J. Sairamesh, (1998). \u201cPrice-war dynamics in a free-market economy of software agents.\u201d In: Proceedings of ALIFE-VI, Los Angeles."},{"key":"13_CR6","doi-asserted-by":"crossref","DOI":"10.1515\/9780691215747","volume-title":"A Course in Microeconomic Theory","author":"D. Kreps","year":"1990","unstructured":"D. Kreps, (1990). A Course in Microeconomic Theory. Princeton NJ: Princeton University Press."},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"M. L. Littman, (1994). \u201cMarkov games as a framework for multi-agent reinforcement learning,\u201d Proceedings of the Eleventh International Conference on Machine Learning, 157\u2013163, Morgan Kaufmann.","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"J. Sairamesh and J. O. Kephart, (1998). \u201cDynamics of price and quality differentiation in information and computational markets.\u201d Proceedings of the First International Conference on Information and Computation Economics (ICE-98), 28\u201336, ACM Press.","DOI":"10.1145\/288994.289000"},{"key":"13_CR9","unstructured":"T. W. Sandholm and R. H. Crites, (1995). \u201cOn multiagent Q-Learning in a semi-competitive domain.\u201d 14th International Joint Conference on Artificial Intelligence (IJCAI-95), Workshop on Adaptation and Learning in Multiagent Systems, Montreal, Canada, 71\u201377."},{"key":"13_CR10","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1145\/301136.301195","volume-title":"Proceedings of the Third International Conference on Autonomous Agents","author":"P. Stone","year":"1999","unstructured":"P. Stone and M. Veloso, (1999). \u201cTeam-partitioned, opaque-transition reinforcement learning.\u201d Proceedings of the Third International Conference on Autonomous Agents, 206\u2013212. New York: ACM Press."},{"issue":"3","key":"13_CR11","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G. Tesauro","year":"1995","unstructured":"G. Tesauro, (1995). \u201cTemporal difference learning and TD-Gammon.\u201d Comm. of the ACM, 38:3, 58\u201367.","journal-title":"Comm. of the ACM"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"G. J. Tesauro and J. O. Kephart, (2000). \u201cForesight-based pricing algorithms in agent economies.\u201d Decision Support Sciences, to appear.","DOI":"10.1016\/S0167-9236(99)00074-3"},{"issue":"3","key":"13_CR13","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1080\/095281398146770","volume":"10","author":"J. M. Vidal","year":"1998","unstructured":"J. M. Vidal and E. H. Durfee, (1998). \u201cLearning nested agent models in an information economy,\u201d J. of Experimental and Theoretical AI, 10(3), 291\u2013308.","journal-title":"J. of Experimental and Theoretical AI"},{"key":"13_CR14","unstructured":"C. J. C. H. Watkins, (1989). \u201cLearning from delayed rewards.\u201d Doctoral dissertation, Cambridge University."},{"key":"13_CR15","first-page":"279","volume":"8","author":"C. J. C. H. Watkins","year":"1992","unstructured":"C. J. C. H. Watkins and P. Dayan, (1992). \u201cQ-learning.\u201d Machine Learning 8, 279\u2013292.","journal-title":"Machine Learning"},{"key":"13_CR16","unstructured":"W. Zhang and T. G. Dietterich, (1996). \u201cHigh-performance job-shop scheduling with a time-delay TD(\u03bb) network.\u201d In: D. Touretzky et al., eds., Advances in Neural Information Processing Systems 8, 1024\u20131030, MIT Press."}],"container-title":["Lecture Notes in Computer Science","Sequence Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-44565-X_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,21]],"date-time":"2021-08-21T15:36:04Z","timestamp":1629560164000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-44565-X_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2000]]},"ISBN":["9783540415978","9783540445654"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/3-540-44565-x_13","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2000]]}}}