{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T19:10:10Z","timestamp":1743621010796,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819642069","type":"print"},{"value":"9789819642076","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\/978-981-96-4207-6_45","type":"book-chapter","created":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T18:38:28Z","timestamp":1743619108000},"page":"503-514","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning for\u00a0Airline Multi-product Continuous Dynamic Pricing"],"prefix":"10.1007","author":[{"given":"Zhicheng","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenguo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,1]]},"reference":[{"issue":"8","key":"45_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. Manage. Sci. 40(8), 999\u20131020 (1994)","journal-title":"Manage. Sci."},{"issue":"1","key":"45_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."},{"issue":"1","key":"45_CR3","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. Manage. Sci. 50(1), 15\u201333 (2004)","journal-title":"Manage. Sci."},{"key":"45_CR4","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. Rev. Pric. Manag. 17, 63\u201377 (2018). https:\/\/doi.org\/10.1057\/s41272-017-0120-2","journal-title":"J. Rev. Pric. Manag."},{"key":"45_CR5","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."},{"key":"45_CR6","first-page":"332","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. Rev. Pric. Manage. 19, 332\u2013348 (2020)","journal-title":"J. Rev. Pric. Manage."},{"key":"45_CR7","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1057\/s41272-021-00285-3","volume":"21","author":"A Kastius","year":"2022","unstructured":"Kastius, A., Schlosser, R.: Dynamic pricing under competition using reinforcement learning. J. Rev. Pric. Manag. 21, 50\u201363 (2022). https:\/\/doi.org\/10.1057\/s41272-021-00285-3","journal-title":"J. Rev. Pric. Manag."},{"key":"45_CR8","doi-asserted-by":"publisher","first-page":"108073","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":"45_CR9","unstructured":"Belobaba, P.P.: Optimal vs. heuristic methods for nested seat allocation. Presentation at ORSA\/TIMS Joint National Meeting (1992)"},{"key":"45_CR10","unstructured":"Bratu, S.: Network value concept in airline revenue management. Master\u2019s thesis, Massachusetts Institute of Technology (1998)"},{"issue":"2","key":"45_CR11","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. Transp. Sci. 33(2), 136\u2013146 (1999)","journal-title":"Transp. Sci."},{"key":"45_CR12","unstructured":"Williamson, E.L.: Airline network seat inventory control: methodologies and revenue impacts. Ph.D. thesis, Massachusetts Institute of Technology (1992)"},{"key":"45_CR13","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":"45_CR14","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":"45_CR15","doi-asserted-by":"publisher","first-page":"121252","DOI":"10.1016\/j.eswa.2023.121252","volume":"237","author":"W Qiao","year":"2023","unstructured":"Qiao, W., et al.: Distributed dynamic pricing of multiple perishable products using multi-agent reinforcement learning. Expert Syst. Appl. 237, 121252 (2023)","journal-title":"Expert Syst. Appl."},{"key":"45_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, abs\/1801.01290 (2018)"},{"key":"45_CR17","unstructured":"Ng, A., et al.: Policy invariance under reward transformations: theory and application to reward shaping. In: International Conference on Machine Learning (1999)"}],"container-title":["Lecture Notes in Computer Science","Parallel and Distributed Computing, Applications and Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-4207-6_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T18:38:30Z","timestamp":1743619110000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-4207-6_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819642069","9789819642076"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-4207-6_45","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":"1 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PDCAT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel and Distributed Computing: Applications and Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","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":"14 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pdcat2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/hpcc.siat.ac.cn\/meeting\/pdcat2024\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}