{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:52:54Z","timestamp":1786067574565,"version":"3.56.0"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2002,9,1]],"date-time":"2002-09-01T00:00:00Z","timestamp":1030838400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2002,9,1]],"date-time":"2002-09-01T00:00:00Z","timestamp":1030838400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Autonomous Agents and Multi-Agent Systems"],"published-print":{"date-parts":[[2002,9]]},"DOI":"10.1023\/a:1015504423309","type":"journal-article","created":{"date-parts":[[2002,12,28]],"date-time":"2002-12-28T23:59:19Z","timestamp":1041119959000},"page":"289-304","source":"Crossref","is-referenced-by-count":91,"title":["Pricing in Agent Economies Using Multi-Agent Q-Learning"],"prefix":"10.1007","volume":"5","author":[{"given":"Gerald","family":"Tesauro","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey O.","family":"Kephart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"408185_CR1","unstructured":"R. H. Crites and A. G. Improving elevator performance using reinforcement learning,\u201d in D. Touretzky et al. (eds.), Advances in Neural Information Processing Systems, MIT Press, 1996, vol. 8, pp. 1017-1023."},{"key":"408185_CR2","volume-title":"Game Theory","author":"D. Fudenberg","year":"1991","unstructured":"D. Fudenberg and J. Tirole, Game Theory, MIT Press: Cambridge, MA: 1991."},{"key":"408185_CR3","doi-asserted-by":"crossref","unstructured":"A. Greenwald and J. O. Kephart, \u201cShopbots and pricebots,\u201d to appear in: Proc. IJCAI-99, 1999.","DOI":"10.1007\/10720026_1"},{"key":"408185_CR4","unstructured":"J. Hu and M. P.Wellman, \u201cMultiagent reinforcement learning: theoretical framework and an algorithm,\u201d Proc. ICML-98, 1998."},{"key":"408185_CR5","doi-asserted-by":"crossref","unstructured":"J. O. Kephart, J. E. Hanson and, J. Sairamesh, \u201cPrice-war dynamics in a free-market economy of software agents Proc. ALIFE-VI, Los Angeles, 1998.","DOI":"10.1162\/106454698568413"},{"key":"408185_CR6","doi-asserted-by":"crossref","DOI":"10.1515\/9780691215747","volume-title":"A Course in Microeconomic Theory","author":"D. Kreps","year":"1990","unstructured":"D. Kreps, A Course in Microeconomic Theory, Princeton Univ. Press: Princeton, NJ, 1990."},{"key":"408185_CR7","doi-asserted-by":"crossref","unstructured":"M. L. Littman, \u201cMarkov games as a framework for multi-agent reinforcement learning,\u201d Proc. Eleventh Int. Conf. Machine Learning, Morgan Kaufmann, 1994, pp. 157-163.","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"408185_CR8","doi-asserted-by":"crossref","unstructured":"J. Sairamesh and J. O. Kephart, \u201cDynamics of price and quality differentiation in information and computational markets,\u201d Proc. First Int. Conf. Information and Computation Economics (ICE-98), ACM Press, 1998, pp. 28-36.","DOI":"10.1145\/288994.289000"},{"key":"408185_CR9","unstructured":"T. W. Sandholm and R. H. Crites, \u201cOn multiagent Q-Learning in a semi-competitive domain,\u201d 14th Int. Joint Conf. Artificial Intelligence (IJCAI-95) Workshop on Adaptation and Learning in Multiagent Systems, Montreal, Canada, 1995, pp. 71\u201377."},{"key":"408185_CR10","unstructured":"M. Sridharan and G. Tesauro, \u201cMulti-agent Q-learning and regression trees for automated pricing decisions,\u201d Proc. ICML-00, to appear, 2000."},{"issue":"3","key":"408185_CR11","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G. Tesauro","year":"1995","unstructured":"G. Tesauro, \u201cTemporal difference learning and TD-Gammon,\u201d Comm. of the ACM, vol. 38, no. 3, pp. 58-67, 1995.","journal-title":"Comm. of the ACM"},{"key":"408185_CR12","doi-asserted-by":"crossref","unstructured":"G. J. Tesauro and J. O. Kephart, \u201cForesight-based pricing algorithms in an economy of software agents,\u201d Proc. First Int. Conf. Information and Computation Economics (ICE-98), ACM Press, 1998, pp. 37-44.","DOI":"10.1145\/288994.289002"},{"key":"408185_CR13","doi-asserted-by":"crossref","unstructured":"G. J. Tesauro and J. O. Kephart, \u201cForesight-based pricing algorithms in agent economies,\u201d Decision Support Sciences, to appear, 1999.","DOI":"10.1145\/288994.289002"},{"key":"408185_CR14","doi-asserted-by":"crossref","unstructured":"J. M. Vidal and E. H. Durfee, \u201cLearning nested agent models in an information economy,\u201d J. Experimental and Theoretical AI, to appear, 1998.","DOI":"10.1080\/095281398146770"},{"key":"408185_CR15","unstructured":"C. J. C. H. Watkins, \u201cLearning from delayed rewards,\u201d Ph.D. thesis, Cambridge University, 1989."},{"key":"408185_CR16","first-page":"279","volume":"8","author":"C. J. C. H. Watkins","year":"1992","unstructured":"C. J. C. H. Watkins and P. Dayan, \u201cQ-learning,\u201d Machine Learning, vol. 8, pp. 279-292, 1992.","journal-title":"Machine Learning"},{"key":"408185_CR17","unstructured":"W. Zhang and T. G. Dietterich, \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, am Press, 1996, vol. 8, pp. 1024-1030."}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1015504423309.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1015504423309\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1015504423309.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T06:14:39Z","timestamp":1747462479000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1015504423309"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,9]]},"references-count":17,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2002,9]]}},"alternative-id":["408185"],"URL":"https:\/\/doi.org\/10.1023\/a:1015504423309","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2002,9]]}}}