{"id":"https://openalex.org/W2907543530","doi":"https://doi.org/10.1109/icdm.2018.00077","title":"Deep Reinforcement Learning with Knowledge Transfer for Online Rides Order Dispatching","display_name":"Deep Reinforcement Learning with Knowledge Transfer for Online Rides Order Dispatching","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2907543530","doi":"https://doi.org/10.1109/icdm.2018.00077","mag":"2907543530"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2018.00077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2018.00077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-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/A5100641626","display_name":"Zhaodong Wang","orcid":"https://orcid.org/0000-0003-3112-077X"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhaodong Wang","raw_affiliation_strings":["Washington State University, Pullman, WA"],"affiliations":[{"raw_affiliation_string":"Washington State University, Pullman, WA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085579946","display_name":"Zhiwei Qin","orcid":"https://orcid.org/0000-0001-5383-4816"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiwei Qin","raw_affiliation_strings":["Washington State University, Pullman, WA"],"affiliations":[{"raw_affiliation_string":"Washington State University, Pullman, WA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101670036","display_name":"Xiaocheng Tang","orcid":"https://orcid.org/0000-0003-1009-9879"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaocheng Tang","raw_affiliation_strings":["DiDi Research America, Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"DiDi Research America, Mountain View, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010419481","display_name":"Jieping Ye","orcid":"https://orcid.org/0000-0001-8662-5818"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieping Ye","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077961759","display_name":"Hongtu Zhu","orcid":"https://orcid.org/0000-0002-6781-2690"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtu Zhu","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100641626"],"corresponding_institution_ids":["https://openalex.org/I72951846"],"apc_list":null,"apc_paid":null,"fwci":8.4004,"has_fulltext":false,"cited_by_count":110,"citation_normalized_percentile":{"value":0.97847717,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"617","last_page":"626"},"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/T12392","display_name":"Sharing Economy and Platforms","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10698","display_name":"Transportation Planning and Optimization","score":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8504176735877991},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7844867706298828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.750151515007019},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7033592462539673},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6188256144523621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5088634490966797},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4831952154636383},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4662417769432068},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46174508333206177},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.45734333992004395},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.441400945186615},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43823572993278503},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.4323922395706177},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16745784878730774},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.12246119976043701}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8504176735877991},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7844867706298828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750151515007019},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7033592462539673},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6188256144523621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088634490966797},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4831952154636383},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4662417769432068},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46174508333206177},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45734333992004395},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.441400945186615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43823572993278503},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.4323922395706177},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16745784878730774},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.12246119976043701},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm.2018.00077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2018.00077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W101796584","https://openalex.org/W156001215","https://openalex.org/W1585855589","https://openalex.org/W1988580225","https://openalex.org/W1991874986","https://openalex.org/W2053913299","https://openalex.org/W2061069829","https://openalex.org/W2065195978","https://openalex.org/W2097381042","https://openalex.org/W2100495367","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2165698076","https://openalex.org/W2174786457","https://openalex.org/W2237537322","https://openalex.org/W2426267443","https://openalex.org/W2560647685","https://openalex.org/W2735995851","https://openalex.org/W2739083961","https://openalex.org/W2740302738","https://openalex.org/W2742211145","https://openalex.org/W2746553466","https://openalex.org/W2757649114","https://openalex.org/W2808810245","https://openalex.org/W2950678851","https://openalex.org/W2963049866","https://openalex.org/W2963199420","https://openalex.org/W4214717370","https://openalex.org/W4297744728","https://openalex.org/W4298174377","https://openalex.org/W4319988532","https://openalex.org/W6606267662","https://openalex.org/W6665721359","https://openalex.org/W6674600207","https://openalex.org/W6690067395","https://openalex.org/W6740879895","https://openalex.org/W6744432492"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2315999538","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Ride":[0],"dispatching":[1,25,46,57,76,141],"is":[2],"a":[3,8,28,95,148],"central":[4],"operation":[5],"task":[6,63],"on":[7,37,50],"ride-sharing":[9,51,72],"platform":[10],"to":[11,15,43,151],"continuously":[12],"match":[13],"drivers":[14,49],"trip-requesting":[16],"passengers.":[17],"In":[18],"this":[19,60],"work,":[20],"we":[21,93,124],"model":[22],"the":[23,45,70,126,159],"ride":[24],"problem":[26],"as":[27],"Markov":[29],"Decision":[30],"Process":[31],"and":[32,55,91,115,128],"propose":[33,94],"learning":[34,89,98,127,135],"solutions":[35],"based":[36],"deep":[38,133],"Q-networks":[39],"with":[40,83,105],"action":[41],"search":[42],"optimize":[44],"policy":[47],"for":[48,59],"platforms.":[52],"We":[53,137],"train":[54],"evaluate":[56],"agents":[58],"challenging":[61],"decision":[62],"using":[64],"real-world":[65],"spatio-temporal":[66],"trip":[67],"data":[68],"from":[69,147],"DiDi":[71],"platform.":[73],"A":[74],"large-scale":[75],"system":[77],"typically":[78],"supports":[79],"many":[80],"geographical":[81],"locations":[82],"diverse":[84],"demand-supply":[85],"settings.":[86],"To":[87],"increase":[88],"adaptability":[90],"efficiency,":[92],"new":[96],"transfer":[97,111,166],"method":[99],"Correlated":[100],"Feature":[101],"Progressive":[102],"Transfer,":[103],"along":[104],"two":[106],"existing":[107],"methods,":[108],"enabling":[109],"knowledge":[110,146],"in":[112],"both":[113],"spatial":[114],"temporal":[116,156],"spaces.":[117],"Through":[118],"an":[119],"extensive":[120],"set":[121],"of":[122,131],"experiments,":[123],"demonstrate":[125],"optimization":[129],"capabilities":[130],"our":[132],"reinforcement":[134],"algorithms.":[136],"further":[138],"show":[139],"that":[140],"policies":[142],"learned":[143],"by":[144],"transferring":[145],"source":[149],"city":[150,161],"target":[152],"cities":[153],"or":[154],"across":[155],"space":[157],"within":[158],"same":[160],"significantly":[162],"outperform":[163],"those":[164],"without":[165],"learning.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":12}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}