{"id":"https://openalex.org/W7224994282","doi":"https://doi.org/10.1016/j.tbs.2026.101429","title":"Adapting service behavior of taxi drivers for optimal operating decisions via distributional reinforcement learning","display_name":"Adapting service behavior of taxi drivers for optimal operating decisions via distributional reinforcement learning","publication_year":2026,"publication_date":"2026-10-31","ids":{"openalex":"https://openalex.org/W7224994282","doi":"https://doi.org/10.1016/j.tbs.2026.101429"},"language":"en","primary_location":{"id":"doi:10.1016/j.tbs.2026.101429","doi":"https://doi.org/10.1016/j.tbs.2026.101429","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.tbs.2026.101429","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2214367X26001985/pdf","source":{"id":"https://openalex.org/S2764874763","display_name":"Travel Behaviour and Society","issn_l":"2214-367X","issn":["2214-367X","2214-3688"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","cwts-core","dongbi-b","erih-plus","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Travel Behaviour and Society","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.sciencedirect.com/science/article/pii/S2214367X26001985/pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138514210","display_name":"Zaoli Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zaoli Yang","raw_affiliation_strings":["School of Economics and Management, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160245962","display_name":"Yixiang Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixiang Ma","raw_affiliation_strings":["School of Economics and Management, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160244482","display_name":"Weijian Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weijian Zhang","raw_affiliation_strings":["Polixir Technologies Co., Ltd, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polixir Technologies Co., Ltd, Nanjing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070515528","display_name":"Vincent Charles","orcid":"https://orcid.org/0000-0001-8943-5681","observed_orcids":["https://orcid.org/0000-0001-8943-5681"]},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vincent Charles","raw_affiliation_strings":["Queen\u2019s Business School, Queen\u2019s University Belfast, Belfast, BT9 5EE, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen\u2019s Business School, Queen\u2019s University Belfast, Belfast, BT9 5EE, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160273794","display_name":"Kun Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022532351","display_name":"Wen\u2010Long Shang","orcid":"https://orcid.org/0000-0002-9162-901X","observed_orcids":["https://orcid.org/0000-0002-9162-901X"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Wen-Long Shang","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022532351"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":{"value":2850,"currency":"USD","value_usd":2850},"apc_paid":{"value":2850,"currency":"USD","value_usd":2850},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74449501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"46","issue":null,"first_page":"101429","last_page":"101429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.6650000214576721,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.6650000214576721,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10698","display_name":"Transportation Planning and Optimization","score":0.07919999957084656,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.07900000363588333,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/taxi-dispatch","display_name":"taxi dispatch","score":0.9300000071525574},{"id":"https://openalex.org/keywords/distributional-reinforcement-learning","display_name":"distributional reinforcement learning","score":0.949999988079071},{"id":"https://openalex.org/keywords/risk-preferences","display_name":"risk preferences","score":0.8889999985694885}],"concepts":[{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.705299973487854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6553000211715698},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6176000237464905},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5385000109672546},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5078999996185303},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.4050000011920929},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C195487862","wikidata":"https://www.wikidata.org/wiki/Q850210","display_name":"Revenue","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C63817138","wikidata":"https://www.wikidata.org/wiki/Q3455889","display_name":"Quantile regression","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C68784500","wikidata":"https://www.wikidata.org/wiki/Q1570691","display_name":"Adaptive behavior","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C2778174566","wikidata":"https://www.wikidata.org/wiki/Q2874240","display_name":"Loss aversion","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C2779449553","wikidata":"https://www.wikidata.org/wiki/Q5194187","display_name":"Cumulative prospect theory","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29269999265670776},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C205706631","wikidata":"https://www.wikidata.org/wiki/Q2319304","display_name":"Expected utility hypothesis","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C181889124","wikidata":"https://www.wikidata.org/wiki/Q380204","display_name":"Service level","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C339426","wikidata":"https://www.wikidata.org/wiki/Q1151839","display_name":"Prospect theory","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.tbs.2026.101429","doi":"https://doi.org/10.1016/j.tbs.2026.101429","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.tbs.2026.101429","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2214367X26001985/pdf","source":{"id":"https://openalex.org/S2764874763","display_name":"Travel Behaviour and Society","issn_l":"2214-367X","issn":["2214-367X","2214-3688"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","cwts-core","dongbi-b","erih-plus","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Travel Behaviour and Society","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.tbs.2026.101429","doi":"https://doi.org/10.1016/j.tbs.2026.101429","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.tbs.2026.101429","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2214367X26001985/pdf","source":{"id":"https://openalex.org/S2764874763","display_name":"Travel Behaviour and Society","issn_l":"2214-367X","issn":["2214-367X","2214-3688"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","cwts-core","dongbi-b","erih-plus","jufo-1","ki-jl-1","norway-1","poland-100","russia-white-list-1","vabb-shw"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Travel Behaviour and Society","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7552000284194946,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"},{"score":0.428600013256073,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G7744820177","display_name":null,"funder_award_id":"72371005","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224994282.pdf","grobid_xml":"https://content.openalex.org/works/W7224994282.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2103253102","https://openalex.org/W2695874637","https://openalex.org/W2761873684","https://openalex.org/W2765302304","https://openalex.org/W2808035253","https://openalex.org/W2946789497","https://openalex.org/W2973371563","https://openalex.org/W2981604716","https://openalex.org/W2998436408","https://openalex.org/W3008343234","https://openalex.org/W3015295488","https://openalex.org/W3029687524","https://openalex.org/W3035460113","https://openalex.org/W3038371177","https://openalex.org/W3089575620","https://openalex.org/W3118248542","https://openalex.org/W3133529384","https://openalex.org/W3174022889","https://openalex.org/W3181461345","https://openalex.org/W3183225583","https://openalex.org/W3190396186","https://openalex.org/W3199357765","https://openalex.org/W3212678506","https://openalex.org/W3215339582","https://openalex.org/W3215360979","https://openalex.org/W4207021923","https://openalex.org/W4210497946","https://openalex.org/W4308780247","https://openalex.org/W4400048783","https://openalex.org/W4401047196","https://openalex.org/W4403262390","https://openalex.org/W4403904911","https://openalex.org/W4411603919","https://openalex.org/W4412979743","https://openalex.org/W7164481090"],"related_works":["https://openalex.org/W3095747859","https://openalex.org/W3046375616","https://openalex.org/W2796438394","https://openalex.org/W3190396186","https://openalex.org/W4387913915","https://openalex.org/W3195185296","https://openalex.org/W4206979206","https://openalex.org/W4391409117","https://openalex.org/W3003540860","https://openalex.org/W7164862233"],"abstract_inverted_index":{"Taxi":[0],"drivers\u2019":[1,44],"area":[2],"choices":[3],"shape":[4],"subsequent":[5],"locations,":[6],"order":[7],"availability,":[8],"and":[9,26,48,72,127,136,152,159,176],"cumulative":[10],"earnings,":[11],"yet":[12],"previous":[13],"intelligent":[14],"transport":[15],"studies":[16],"prioritize":[17],"passenger-demand":[18],"matching":[19],"or":[20],"expected":[21],"returns,":[22],"overlooking":[23],"sequential":[24],"dependence":[25],"heterogeneous":[27,164],"risk":[28,165],"preferences.":[29,138,166],"This":[30],"study":[31,193],"formulates":[32],"taxi":[33,43,118],"dispatch":[34,190],"as":[35],"a":[36,50,73,108],"risk-sensitive,":[37],"multi-step":[38],"decision":[39,181],"problem":[40],"to":[41,56,163],"support":[42],"adaptive":[45],"service":[46,206,211],"behavior":[47,207],"proposes":[49],"weighted":[51],"implicit":[52,65,128],"quantile":[53,66,95,102,129],"network":[54,67,130],"(wIQN)":[55],"optimize":[57],"long-horizon":[58,185],"operating":[59],"revenue.":[60],"wIQN":[61,106,143],"extends":[62],"the":[63,84,145,202],"standard":[64],"with":[68,122],"target-quantile-aware":[69],"temporal-difference":[70],"weighting":[71],"correction":[74],"for":[75,201],"extreme":[76],"negative":[77],"weights,":[78],"thereby":[79],"preserving":[80,171],"informative":[81],"variation":[82],"in":[83,107,208],"return":[85,155],"distribution.":[86],"It":[87],"further":[88],"separates":[89],"preference-neutral":[90],"distribution":[91],"learning":[92],"through":[93,101],"uniform":[94],"sampling":[96],"from":[97,113],"preference-specific":[98],"policy":[99],"selection":[100],"distortion.":[103],"We":[104],"evaluate":[105],"week-long":[109],"offline":[110],"simulation":[111],"built":[112],"2019":[114],"New":[115],"York":[116],"City":[117],"trips,":[119],"comparing":[120],"it":[121],"greedy,":[123],"deep":[124],"Q-network":[125],"(DQN),":[126],"(IQN)":[131],"policies":[132],"under":[133],"risk-averse,":[134],"risk-neutral,":[135],"risk-seeking":[137],"The":[139,192],"results":[140],"show":[141],"that":[142,170],"achieves":[144],"strongest":[146],"weekly":[147],"revenue":[148],"performance,":[149],"learns":[150],"broader":[151],"more":[153],"differentiated":[154],"distributions":[156],"than":[157],"IQN,":[158],"produces":[160],"clearer":[161],"responses":[162],"These":[167],"findings":[168],"indicate":[169],"return-distribution":[172],"detail":[173],"during":[174],"training":[175],"postponing":[177],"preference":[178],"distortion":[179],"until":[180],"time":[182],"can":[183],"improve":[184],"decisions":[186],"while":[187],"supporting":[188],"personalized":[189],"recommendations.":[191],"contributes":[194],"an":[195],"operator-centered,":[196],"risk-sensitive":[197],"distributional":[198],"reinforcement-learning":[199],"framework":[200],"model-driven":[203],"adaptation":[204],"of":[205],"dynamic":[209],"urban":[210],"systems.":[212]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-11-01T00:00:00"}