{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T10:10:09Z","timestamp":1746439809226,"version":"3.40.4"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819644445","type":"print"},{"value":"9789819644452","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-4445-2_5","type":"book-chapter","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T09:33:50Z","timestamp":1746437630000},"page":"56-68","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning for\u00a0Airline Continuous Dynamic Pricing"],"prefix":"10.1007","author":[{"given":"Zhicheng","family":"Yao","sequence":"first","affiliation":[]},{"given":"Wenguo","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,6]]},"reference":[{"issue":"8","key":"5_CR1","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1287\/mnsc.40.8.999","volume":"40","author":"G Gallego","year":"1994","unstructured":"Gallego, G., van Ryzin, G.: Optimal dynamic pricing of inventories with stochastic demand over finite horizons. Manag. Sci. 40(8), 999\u20131020 (1994)","journal-title":"Manag. Sci."},{"issue":"1","key":"5_CR2","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1287\/opre.45.1.24","volume":"45","author":"G Gallego","year":"1997","unstructured":"Gallego, G., van Ryzin, G.: A multiproduct dynamic pricing problem and its applications to network yield management. Oper. Res. 45(1), 24\u201341 (1997)","journal-title":"Oper. Res."},{"key":"5_CR3","unstructured":"Belobaba, P.P.: Optimal vs. heuristic methods for nested seat allocation. In: Presentation at ORSA\/TIMS Joint National Meeting (1992)"},{"issue":"2","key":"5_CR4","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1287\/trsc.33.2.136","volume":"33","author":"CJ Lautenbacher","year":"1999","unstructured":"Lautenbacher, C.J., Stidham, S., Jr.: The underlying Markov decision process in the single-leg airline yield-management problem. Transport. Sci. 33(2), 136\u2013146 (1999)","journal-title":"Transport. Sci."},{"issue":"1","key":"5_CR5","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1287\/mnsc.1030.0147","volume":"50","author":"K Talluri","year":"2004","unstructured":"Talluri, K., van Ryzin, G.: Revenue management under a general discrete choice model of consumer behavior. Manag. Sci. 50(1), 15\u201333 (2004)","journal-title":"Manag. Sci."},{"key":"5_CR6","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1057\/s41272-017-0120-2","volume":"17","author":"R Kumar","year":"2018","unstructured":"Kumar, R., Li, A., Wang, W.: Learning and optimizing through dynamic pricing. J. Revenue Pricing Manag. 17, 63\u201377 (2018). https:\/\/doi.org\/10.1057\/s41272-017-0120-2","journal-title":"J. Revenue Pricing Manag."},{"key":"5_CR7","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.ejor.2014.09.038","volume":"242","author":"DF Otero","year":"2015","unstructured":"Otero, D.F., Akhavan-Tabatabaei, R.: A stochastic dynamic pricing model for the multiclass problems in the airline industry. Eur. J. Oper. Res. 242, 188\u2013200 (2015)","journal-title":"Eur. J. Oper. Res."},{"issue":"8","key":"5_CR8","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1287\/mnsc.1100.1178","volume":"56","author":"Y Ak\u00e7ay","year":"2010","unstructured":"Ak\u00e7ay, Y., Natarajan, H.P., Xu, S.H.: Joint dynamic pricing of multiple perishable products under consumer choice. Manag. Sci. 56(8), 1345\u20131361 (2010). https:\/\/doi.org\/10.1287\/mnsc.1100.1178","journal-title":"Manag. Sci."},{"key":"5_CR9","doi-asserted-by":"publisher","first-page":"1191","DOI":"10.1016\/j.jmaa.2019.06.012","volume":"478","author":"AM Selcuk","year":"2019","unstructured":"Selcuk, A.M., Avsar, Z.M.: Dynamic pricing in airline revenue management. J. Math. Anal. Appl. 478, 1191\u20131217 (2019). https:\/\/doi.org\/10.1016\/j.jmaa.2019.06.012","journal-title":"J. Math. Anal. Appl."},{"key":"5_CR10","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1080\/07408170208928908","volume":"34","author":"A Gosavii","year":"2002","unstructured":"Gosavii, A., Bandla, N., Das, T.K.: A reinforcement learning approach to a single leg airline revenue management problem with multiple fare classes and overbooking. IIE Trans. 34, 729\u2013742 (2002)","journal-title":"IIE Trans."},{"key":"5_CR11","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/B:MACH.0000019802.64038.6c","volume":"55","author":"A Gosavi","year":"2004","unstructured":"Gosavi, A.: A reinforcement learning algorithm based on policy iteration for average reward: empirical results with yield management and convergence analysis. Mach. Learn. 55, 5\u201329 (2004)","journal-title":"Mach. Learn."},{"key":"5_CR12","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1016\/j.engappai.2019.04.008","volume":"82","author":"RJ Lawhead","year":"2019","unstructured":"Lawhead, R.J., Gosavi, A.: A bounded actor-critic reinforcement learning algorithm applied to airline revenue management. Eng. Appl. Artif. Intell. 82, 252\u2013262 (2019)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"5_CR13","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1057\/s41272-020-00228-4","volume":"19","author":"N Bondoux","year":"2020","unstructured":"Bondoux, N., Nguyen, A.Q., Fiig, T., Acuna-Agost, R.: Reinforcement learning applied to airline revenue management. J. Revenue Pricing Manag. 19, 332\u2013348 (2020)","journal-title":"J. Revenue Pricing Manag."},{"key":"5_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108073","volume":"133","author":"S Jo","year":"2024","unstructured":"Jo, S., Lee, G.M., Moon, I.: Airline dynamic pricing with patient customers using deep exploration-based reinforcement learning. Eng. Appl. Artif. Intell. 133, 108073 (2024)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"5_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2024.110302","volume":"193","author":"X Zhu","year":"2024","unstructured":"Zhu, X., Jian, L., Chen, X., Zhao, Q.: Reinforcement learning for multi-flight dynamic pricing. Comput. Ind. Eng. 193, 110302 (2024)","journal-title":"Comput. Ind. Eng."},{"key":"5_CR16","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. ArXiv arxiv:1801.01290 (2018)"},{"key":"5_CR17","unstructured":"Devlin, S., Kudenko, D.: Dynamic potential-based reward shaping. In: Adaptive Agents and Multi-Agent Systems (2012)"}],"container-title":["Lecture Notes in Computer Science","Combinatorial Optimization and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-4445-2_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T09:33:52Z","timestamp":1746437632000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-4445-2_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819644445","9789819644452"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-4445-2_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"6 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"COCOA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Combinatorial Optimization and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"6 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cocoa2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cocoa2024.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}