{"id":"https://openalex.org/W2979079868","doi":"https://doi.org/10.1145/3357384.3357799","title":"Multi-Agent Reinforcement Learning for Order-dispatching via Order-Vehicle Distribution Matching","display_name":"Multi-Agent Reinforcement Learning for Order-dispatching via Order-Vehicle Distribution Matching","publication_year":2019,"publication_date":"2019-11-03","ids":{"openalex":"https://openalex.org/W2979079868","doi":"https://doi.org/10.1145/3357384.3357799","mag":"2979079868"},"language":"en","primary_location":{"id":"doi:10.1145/3357384.3357799","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3357799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.02591","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ming Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ming Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiarui Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarui Jin","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weinan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weinan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiwei Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiwei Qin","raw_affiliation_strings":["DiDi AI Labs, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi AI Labs, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yan Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Jiao","raw_affiliation_strings":["DiDi AI Labs, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi AI Labs, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenxi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenxi Wang","raw_affiliation_strings":["DiDi AI Labs, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi AI Labs, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guobin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guobin Wu","raw_affiliation_strings":["DiDi Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yong Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Yu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jieping Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jieping Ye","raw_affiliation_strings":["DiDi AI Labs, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi AI Labs, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":4.3283,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.94288184,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2645","last_page":"2653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":1.0,"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":1.0,"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":0.9961000084877014,"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/T12546","display_name":"Smart Parking Systems Research","score":0.995199978351593,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8051000237464905},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5072000026702881},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45829999446868896},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.3625999987125397},{"id":"https://openalex.org/keywords/hotspot","display_name":"Hotspot (geology)","score":0.34200000762939453},{"id":"https://openalex.org/keywords/intelligent-transportation-system","display_name":"Intelligent transportation system","score":0.328900009393692}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8051000237464905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411999702453613},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5072000026702881},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4172999858856201},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3544999957084656},{"id":"https://openalex.org/C146481406","wikidata":"https://www.wikidata.org/wiki/Q105131","display_name":"Hotspot (geology)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C47796450","wikidata":"https://www.wikidata.org/wiki/Q508378","display_name":"Intelligent transportation system","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3052999973297119},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3357384.3357799","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3357799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.02591","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.02591","pdf_url":"https://arxiv.org/pdf/1910.02591","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.02591","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.02591","pdf_url":"https://arxiv.org/pdf/1910.02591","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1513468570","https://openalex.org/W2103253102","https://openalex.org/W2106251367","https://openalex.org/W2152822538","https://openalex.org/W2569460227","https://openalex.org/W2742211145","https://openalex.org/W2766151308","https://openalex.org/W2768629321","https://openalex.org/W2808810245","https://openalex.org/W2809128166","https://openalex.org/W2889125237","https://openalex.org/W2963934958"],"related_works":[],"abstract_inverted_index":{"Improving":[0],"the":[1,18,79,85,100,106,133,139,148,156,160,180,183],"efficiency":[2],"of":[3,17,45,57,105,164,182,186],"dispatching":[4],"orders":[5,35,48,143],"to":[6,28,49,77,130,137,194],"vehicles":[7,46,140],"is":[8,56,111],"a":[9,67,191],"research":[10],"hotspot":[11],"in":[12,92,162,174],"online":[13,184],"ride-hailing":[14],"systems.":[15],"Most":[16],"existing":[19],"solutions":[20],"for":[21,114],"order-dispatching":[22,70,81],"are":[23,43],"centralized":[24],"controlling,":[25],"which":[26,55],"require":[27],"consider":[29],"all":[30,95],"possible":[31],"matches":[32],"between":[33,119],"available":[34],"and":[36,47,136,142,151,169],"vehicles.":[37],"For":[38],"large-scale":[39,80],"ride-sharing":[40],"platforms,":[41],"there":[42,110],"thousands":[44],"be":[50],"matched":[51],"at":[52,126],"every":[53],"second":[54],"very":[58],"high":[59],"computational":[60],"cost.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,122,189],"propose":[66],"decentralized":[68],"execution":[69],"method":[71,158],"based":[72],"on":[73,146],"multi-agent":[74,88],"reinforcement":[75,89],"learning":[76,90,134],"address":[78],"problem.":[82],"Different":[83],"from":[84,102],"previous":[86],"cooperative":[87],"algorithms,":[91],"our":[93,196],"method,":[94],"agents":[96],"work":[97],"independently":[98],"with":[99,179],"guidance":[101],"an":[103],"evaluation":[104],"joint":[107],"policy":[108],"since":[109],"no":[112],"need":[113],"communication":[115],"or":[116],"explicit":[117],"cooperation":[118],"agents.":[120],"Furthermore,":[121],"use":[123],"KL-divergence":[124],"optimization":[125],"each":[127],"time":[128],"step":[129],"speed":[131],"up":[132],"process":[135],"balance":[138],"(supply)":[141],"(demand).":[144],"Experiments":[145],"both":[147],"explanatory":[149],"environment":[150],"real-world":[152],"simulator":[153],"show":[154],"that":[155],"proposed":[157],"outperforms":[159],"baselines":[161],"terms":[163],"accumulated":[165],"driver":[166],"income":[167],"(ADI)":[168],"Order":[170],"Response":[171],"Rate":[172],"(ORR)":[173],"various":[175],"traffic":[176],"environments.":[177],"Besides,":[178],"support":[181],"platform":[185],"Didi":[187],"Chuxing,":[188],"designed":[190],"hybrid":[192],"system":[193],"deploy":[195],"model.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-10-10T00:00:00"}