{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:09:54Z","timestamp":1742962194089,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031734960"},{"type":"electronic","value":"9783031734977"}],"license":[{"start":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T00:00:00Z","timestamp":1731715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T00:00:00Z","timestamp":1731715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73497-7_29","type":"book-chapter","created":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T04:00:44Z","timestamp":1731643244000},"page":"360-371","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Approximate Nash Equilibrium Learning for\u00a0n-Player Markov Games in Dynamic Pricing"],"prefix":"10.1007","author":[{"given":"Larkin","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,16]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Briesch, R.A., et\u00a0al.: A comparative analysis of reference price models. J. Cons. Res. 24(2), 202\u2013214 (1997)","DOI":"10.1086\/209505"},{"key":"29_CR2","doi-asserted-by":"publisher","unstructured":"Ceppi, S., et\u00a0al.: Local Search Methods for Finding a Nash Equi-librium in Two-Player Games, pp. 335\u2013342 (2010). https:\/\/doi.org\/10.1109\/WI-IAT.2010.57","DOI":"10.1109\/WI-IAT.2010.57"},{"key":"29_CR3","doi-asserted-by":"publisher","unstructured":"Daskalakis, C., Goldberg, P.W., Pa-padimitriou, C.H.: The Complexity of Computing a Nash Equilibrium . In: Proceedings of the Thirty-Eighth Annual ACM Symposium on Theory of Computing, STOC 2006, pp. 71\u201378. Association for Computing Machinery, Seattle, WA, USA (2006). https:\/\/doi.org\/10.1145\/1132516.1132527, isbn: 1595931341","DOI":"10.1145\/1132516.1132527"},{"key":"29_CR4","unstructured":"Diouane, Y., et\u00a0al.: TREGO: a Trust-Region Framework for Efficient Global Optimization. arXiv: org\/abs\/2101.06808 (2021)"},{"key":"29_CR5","unstructured":"Eriksson, D., et\u00a0al.: Scalable Global Optimization via Local Bayesian Optimization. arXiv: 1910.01739 (2019)"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Ferreira, K.J., Alex Lee, B.H., Simchi-Levi, D.: Analytics for an online retailer: Demand forecasting and price optimization. Manufact. Serv. Operations Manag. 18(1), 69\u201388 (2016)","DOI":"10.1287\/msom.2015.0561"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Goeree, J.K., Holt, C.A., Palfrey, T\/R.: Stochastic game theory for social science: a primer on quantal response equilibrium. Cheltenham. Edward Elgar Publishing, UK (2020). https:\/\/www.elgaronline.com\/view\/edcoll\/9781785363320\/9781785363320.xml, isbn: 9781785363320","DOI":"10.4337\/9781785363337.00008"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Michael Harrison, J., Bora Keskin, N., Zeevi, A.: Bayesian dynamic pricing policies: learning and earning under a binary prior distribution. Manag. Sci. 58(3), 570\u2013586 (2012)","DOI":"10.1287\/mnsc.1110.1426"},{"key":"29_CR9","unstructured":"Junling, H., Wellman, M.P.: Nash Q-Learning for General-Sum Stochastic Games. J. Mach. Learn. Res. 4, 1039\u20131069 (2003), issn: 1532-4435"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Janiszewski, C., Lichtenstein, D.R.: A range theory ac-count of price perception. J. Consumer Res. 25(4), 353\u2013368 (1999)","DOI":"10.1086\/209544"},{"key":"29_CR11","unstructured":"Liu, J., et\u00a0al.: Dynamic Pricing on E-commerce Platform with Deep Reinforcement Learning arXiv: 1912.02572 (2019)"},{"key":"29_CR12","unstructured":"Liu, L.: Approximate Nash Equilibrium Learning for n-Player Markov Games in Dynamic Pricing . arXiv preprint arXiv: 2207.06492 (2022)"},{"key":"29_CR13","doi-asserted-by":"publisher","unstructured":"Jue, Liu., Zhan, Pang., Linggang, Qi.: Dynamic pricing and in-ventory management with demand learning: a bayesian approach. Comput. Operations Re. 124, 105078 (2020). https:\/\/doi.org\/10.1016\/j.cor.2020.105078","DOI":"10.1016\/j.cor.2020.105078"},{"key":"29_CR14","unstructured":"Duncan Luce, R.: Individual Choice Behavior: A Theoretical Analysis. Wiley, New York, NY, USA (1959)"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Mnih, V., et\u00a0al.: Human-level control through deep reinforcement learning . Nature 518(7540), 529\u2013533 ( 2015), issn: 00280836","DOI":"10.1038\/nature14236"},{"key":"29_CR16","doi-asserted-by":"publisher","unstructured":"Nash, J.F.: Equilibrium points in n-person games. Proc. Nat. Acad. Sci. 36(1), 48\u201349 (1950). https:\/\/doi.org\/10.1073\/pnas.36.1.48. https:\/\/www.pnas.org\/content\/36\/1\/48issn: 0027-8424","DOI":"10.1073\/pnas.36.1.48"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Porter, R., Nudelman, E., Shoham, Y.: Simple search methods for finding a Nash equilibrium. Games Econ. Behav. 63(2), 642\u2013662 (2008). Second World Congress of the Game Theory Society","DOI":"10.1016\/j.geb.2006.03.015"},{"key":"29_CR18","unstructured":"Ramponi, G., et\u00a0al.: Learning in non-cooperative configurable markov decision processes . In: Beygelzimer, A., et\u00a0al. (ed.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=t-0eCf8L4-a"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Rao, V.R.: Pricing models in marketing. Handbooks Operat. Res. Manag. Sci. 5, 517\u2013552 (1993)","DOI":"10.1016\/S0927-0507(05)80034-9"},{"key":"29_CR20","unstructured":"Raman, K., Bass, F.M., et\u00a0al.: A general test of reference price theory in the presence of threshold effects. In: Tijdschrift voor Economie en management 47(2), 205\u2013226 (2002)"},{"key":"29_CR21","doi-asserted-by":"publisher","unstructured":"Regis, R.G.: Trust regions in Kriging-based optimization with expected improvement. Eng. Optimiz. 48(6), 1037\u20131059 (2016). https:\/\/doi.org\/10.1080\/0305215X.2015.1082350","DOI":"10.1080\/0305215X.2015.1082350"},{"key":"29_CR22","unstructured":"Sayin, M.O., et\u00a0al.: Decentralized Q-Learning in Zero-sum Markov Games, arXiv: 2106.02748 (2021)"},{"key":"29_CR23","doi-asserted-by":"publisher","unstructured":"Thompson, W.R.: On the likelihood that one unknown prob-ability exceeds another in view of evidence of two samples. Biometrika 25(3\u20134), 285\u2013294 (1933). https:\/\/doi.org\/10.1093\/biomet\/25.3-4.285. https:\/\/academic.oup.com\/biomet\/article-pdf\/25\/3-4\/285\/513725\/25-3-4-285.pdf","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Taudes, A., Rudloff, C.: Integrating inventory control and a price change in the presence of reference price effects: a two-period model. Mathem. Methods Operat. Res. 75(1), 29\u201365 (2012)","DOI":"10.1007\/s00186-011-0374-1"},{"issue":"3","key":"29_CR25","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"JCH Christopher","year":"1992","unstructured":"Christopher, J.C.H.: Watkins and Peter Dayan Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992). https:\/\/doi.org\/10.1007\/BF00992698","journal-title":"Mach. Learn."},{"key":"29_CR26","unstructured":"Wang, L., Fonseca, R., Tian, Y.: Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search, arXiv: 2007.00708 (2020)"},{"key":"29_CR27","unstructured":"Wang, X., Sandholm, T.: Reinforcement learning to play an optimal nash equilibrium in team markov games . In: Becker, S., Thrun, S., Obermayer, K. (eds.) Advances in Neural Information Processing Systems. Ed. by . Vol. 15. MIT Press (2003). https:\/\/proceedings.neurips.cc\/paper\/2002\/file\/f8e59f4b2fe7c5705bf878bbd494ccdf-Paper.pdf"}],"container-title":["Lecture Notes in Computer Science","Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73497-7_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T05:10:09Z","timestamp":1731647409000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73497-7_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,16]]},"ISBN":["9783031734960","9783031734977"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73497-7_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,16]]},"assertion":[{"value":"16 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EPIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"EPIA Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Viana do Castelo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"epia2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/epia2024.pt","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}