{"id":"https://openalex.org/W3152848684","doi":"https://doi.org/10.1145/3442343","title":"Exploring Deep Reinforcement Learning for Task Dispatching in Autonomous On-Demand Services","display_name":"Exploring Deep Reinforcement Learning for Task Dispatching in Autonomous On-Demand Services","publication_year":2021,"publication_date":"2021-04-21","ids":{"openalex":"https://openalex.org/W3152848684","doi":"https://doi.org/10.1145/3442343","mag":"3152848684"},"language":"en","primary_location":{"id":"doi:10.1145/3442343","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3442343","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","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/A5072565301","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0002-5176-003X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072801590","display_name":"Xi Yu","orcid":"https://orcid.org/0000-0002-0297-9027"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Yu","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740023","display_name":"Jiannong Cao","orcid":"https://orcid.org/0000-0002-2725-2529"},"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":"Jiannong Cao","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072491273","display_name":"Xuxun Liu","orcid":"https://orcid.org/0000-0003-3132-0616"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuxun Liu","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693197","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0002-8629-4622"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, and Huazhong University of Science and Technology, Wuhan, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, and Huazhong University of Science and Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6317,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.66915403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"15","issue":"3","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9979000091552734,"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/T12288","display_name":"Optimization and Search Problems","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7943397760391235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6769943237304688},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6443955898284912},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.626114547252655},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5313302278518677},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5035874247550964},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4711267650127411},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4508032202720642},{"id":"https://openalex.org/keywords/demand-patterns","display_name":"Demand patterns","score":0.4317896366119385},{"id":"https://openalex.org/keywords/demand-response","display_name":"Demand response","score":0.4153895080089569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36305609345436096},{"id":"https://openalex.org/keywords/demand-management","display_name":"Demand management","score":0.22390460968017578},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21524521708488464},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.14069604873657227},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13159659504890442},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1020677387714386},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.09808090329170227}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7943397760391235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769943237304688},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6443955898284912},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.626114547252655},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5313302278518677},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5035874247550964},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4711267650127411},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4508032202720642},{"id":"https://openalex.org/C32597650","wikidata":"https://www.wikidata.org/wiki/Q5255044","display_name":"Demand patterns","level":3,"score":0.4317896366119385},{"id":"https://openalex.org/C2779438525","wikidata":"https://www.wikidata.org/wiki/Q5255048","display_name":"Demand response","level":3,"score":0.4153895080089569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36305609345436096},{"id":"https://openalex.org/C179366874","wikidata":"https://www.wikidata.org/wiki/Q1185130","display_name":"Demand management","level":2,"score":0.22390460968017578},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21524521708488464},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.14069604873657227},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13159659504890442},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1020677387714386},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.09808090329170227},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C206658404","wikidata":"https://www.wikidata.org/wiki/Q12725","display_name":"Electricity","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3442343","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3442343","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2979071180","display_name":null,"funder_award_id":"2020A1515011496","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G3928869049","display_name":"\u534f\u4f5c\u5f0f\u8fb9\u7f18\u8ba1\u7b97\u4e2d\u7f51\u7edc\u611f\u77e5\u7684\u4efb\u52a1\u8c03\u5ea6\u6280\u672f\u7814\u7a76","funder_award_id":"61972161","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"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2065195978","https://openalex.org/W2103253102","https://openalex.org/W2141461755","https://openalex.org/W2145339207","https://openalex.org/W2281858190","https://openalex.org/W2430704425","https://openalex.org/W2525830997","https://openalex.org/W2616545289","https://openalex.org/W2739348915","https://openalex.org/W2742211145","https://openalex.org/W2753741836","https://openalex.org/W2767916855","https://openalex.org/W2770230939","https://openalex.org/W2803846618","https://openalex.org/W2808810245","https://openalex.org/W2907543530","https://openalex.org/W2952281591","https://openalex.org/W2962764167","https://openalex.org/W2963543864","https://openalex.org/W2970142969","https://openalex.org/W2973262936","https://openalex.org/W2985510430","https://openalex.org/W2986725445","https://openalex.org/W3039969618","https://openalex.org/W3099134564","https://openalex.org/W3101169423","https://openalex.org/W3106464996","https://openalex.org/W4249820511"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"Autonomous":[0],"on-demand":[1],"services,":[2],"such":[3,24,27],"as":[4,140],"GOGOX":[5],"(formerly":[6],"GoGoVan)":[7],"in":[8,83,161,168,180,214,236,259,282],"Hong":[9],"Kong,":[10],"provide":[11],"a":[12,28,110,124,158,162,196,200,222,229,252],"platform":[13],"for":[14,20],"users":[15],"to":[16,22,34,40,43,49,63,81,91,108,220,242],"request":[17],"services":[18],"and":[19,56,98,209,287],"suppliers":[21,31,80,99],"meet":[23],"demands.":[25,65],"In":[26,66,133,218],"platform,":[29],"the":[30,38,69,75,84,93,101,115,149,169,176,191,215,226,237,243,247,249,260,275,279],"have":[32],"autonomy":[33],"accept":[35],"or":[36],"reject":[37],"demands":[39,55,82,97,213,227,250],"be":[41,240,263],"dispatched":[42,264],"him/her,":[44],"so":[45],"it":[46,194],"is":[47,72,155],"challenging":[48],"make":[50,137],"an":[51,141],"online":[52],"matching":[53],"between":[54],"suppliers.":[57],"Existing":[58],"methods":[59],"use":[60],"round-based":[61],"approaches":[62],"dispatch":[64],"these":[67],"works,":[68],"dispatching":[70,103,112,127,150,198],"decision":[71,113,151],"based":[73],"on":[74,100,190],"predicted":[76],"response":[77,234,257],"patterns":[78],"of":[79,95,145,152,212,284],"current":[85,102],"round,":[86],"but":[87],"they":[88],"all":[89],"fail":[90],"consider":[92],"impact":[94],"future":[96,116,238,261],"decision.":[104],"This":[105],"could":[106],"lead":[107],"taking":[109],"suboptimal":[111],"from":[114],"perspective.":[117],"To":[118],"solve":[119],"this":[120,134],"problem,":[121],"we":[122,136,272],"propose":[123],"novel":[125],"demand":[126,139],"model":[128,166,277],"using":[129,184,199,269],"deep":[130],"reinforcement":[131],"learning.":[132],"model,":[135],"each":[138,146,153,181],"agent.":[142],"The":[143,165],"action":[144],"agent,":[147],"i.e.,":[148],"demand,":[154],"determined":[156],"by":[157,204],"centralized":[159],"algorithm":[160,203],"coordinated":[163],"way.":[164],"works":[167],"following":[170],"two":[171],"steps.":[172],"(1)":[173],"It":[174],"learns":[175],"demand\u2019s":[177],"expected":[178,210,231,254],"value":[179,232,255],"spatiotemporal":[182],"state":[183],"historical":[185],"transition":[186],"data.":[187],"(2)":[188],"Based":[189],"learned":[192],"values,":[193],"conducts":[195],"Many-To-Many":[197],"combinatorial":[201],"optimization":[202],"considering":[205],"both":[206],"immediate":[207],"rewards":[208],"values":[211],"next":[216,244],"round.":[217,245],"order":[219],"get":[221],"higher":[223],"total":[224],"reward,":[225],"with":[228,251],"high":[230],"(short":[233],"time)":[235,258],"may":[239],"delayed":[241],"On":[246],"contrary,":[248],"low":[253],"(long":[256],"would":[262],"immediately.":[265],"Through":[266],"extensive":[267],"experiments":[268],"real-world":[270],"datasets,":[271],"show":[273],"that":[274],"proposed":[276],"outperforms":[278],"existing":[280],"models":[281],"terms":[283],"Cancellation":[285],"Rate":[286],"Average":[288],"Response":[289],"Time.":[290]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}