{"id":"https://openalex.org/W4414396959","doi":"https://doi.org/10.1016/j.ejor.2025.09.012","title":"Reinforcement learning algorithm for reusable resource allocation with unknown rental time distribution","display_name":"Reinforcement learning algorithm for reusable resource allocation with unknown rental time distribution","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414396959","doi":"https://doi.org/10.1016/j.ejor.2025.09.012"},"language":"en","primary_location":{"id":"doi:10.1016/j.ejor.2025.09.012","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.ejor.2025.09.012","pdf_url":null,"source":{"id":"https://openalex.org/S103321696","display_name":"European Journal of Operational Research","issn_l":"0377-2217","issn":["0377-2217","1872-6860"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"European Journal of Operational Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100389378","display_name":"Ziwei Wang","orcid":"https://orcid.org/0000-0003-0981-1072"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziwei Wang","raw_affiliation_strings":["Department of Industrial Engineering and Management, Peking University, 100871, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0981-1072","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Management, Peking University, 100871, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015181840","display_name":"Jie Song","orcid":"https://orcid.org/0000-0003-2592-8238"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Song","raw_affiliation_strings":["Department of Industrial Engineering and Management, Peking University, 100871, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Management, Peking University, 100871, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119507273","display_name":"Yixuan Liu","orcid":"https://orcid.org/0000-0003-3969-1833"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Liu","raw_affiliation_strings":["Department of Industrial Engineering and Management, Peking University, 100871, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Management, Peking University, 100871, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102015677","display_name":"Jingtong Zhao","orcid":"https://orcid.org/0000-0003-2717-4847"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingtong Zhao","raw_affiliation_strings":["School of Economics, Renmin University of China, 100872, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2717-4847","affiliations":[{"raw_affiliation_string":"School of Economics, Renmin University of China, 100872, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102015677"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":{"value":3290,"currency":"USD","value_usd":3290},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24504532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"331","issue":"1","first_page":"186","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7401999831199646},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.7193999886512756},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6901000142097473},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4912000000476837},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.42579999566078186},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.42500001192092896},{"id":"https://openalex.org/keywords/renting","display_name":"Renting","score":0.42010000348091125},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.40470001101493835},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3953000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717999815940857},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7401999831199646},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7193999886512756},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6901000142097473},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4936000108718872},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4912000000476837},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C85502023","wikidata":"https://www.wikidata.org/wiki/Q157171","display_name":"Renting","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C195487862","wikidata":"https://www.wikidata.org/wiki/Q850210","display_name":"Revenue","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C2781386248","wikidata":"https://www.wikidata.org/wiki/Q11898700","display_name":"Revenue management","level":3,"score":0.3328999876976013},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3050000071525574},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C128669082","wikidata":"https://www.wikidata.org/wiki/Q583461","display_name":"Randomized algorithm","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C49261128","wikidata":"https://www.wikidata.org/wiki/Q1132455","display_name":"Hazard","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.ejor.2025.09.012","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.ejor.2025.09.012","pdf_url":null,"source":{"id":"https://openalex.org/S103321696","display_name":"European Journal of Operational Research","issn_l":"0377-2217","issn":["0377-2217","1872-6860"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"European Journal of Operational Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1516901479","display_name":null,"funder_award_id":"72301282","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1604002124","https://openalex.org/W1978976115","https://openalex.org/W2080050718","https://openalex.org/W2132597332","https://openalex.org/W2154706439","https://openalex.org/W2559983332","https://openalex.org/W2946772172","https://openalex.org/W2952832562","https://openalex.org/W2959895084","https://openalex.org/W2963049774","https://openalex.org/W2977787594","https://openalex.org/W3003964569","https://openalex.org/W3018789859","https://openalex.org/W3020125231","https://openalex.org/W3020324695","https://openalex.org/W3025093529","https://openalex.org/W3035936851","https://openalex.org/W3042977926","https://openalex.org/W3091875946","https://openalex.org/W3097990964","https://openalex.org/W3122960105","https://openalex.org/W3132506527","https://openalex.org/W3213471522","https://openalex.org/W4212833358","https://openalex.org/W4220892975","https://openalex.org/W4246906609","https://openalex.org/W4281481437","https://openalex.org/W4285070958","https://openalex.org/W4285091035","https://openalex.org/W4285163951","https://openalex.org/W4310365801","https://openalex.org/W4310883680","https://openalex.org/W4313019138","https://openalex.org/W4315786078","https://openalex.org/W4384569725","https://openalex.org/W4385720257","https://openalex.org/W4386270094","https://openalex.org/W4400358531","https://openalex.org/W4410031746"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}