{"id":"https://openalex.org/W6912861407","doi":"https://doi.org/10.5555/3635637.3663059","title":"Collaborative Deep Reinforcement Learning for Solving Multi-Objective Vehicle Routing Problems","display_name":"Collaborative Deep Reinforcement Learning for Solving Multi-Objective Vehicle Routing Problems","publication_year":2024,"publication_date":"2024-05-01","ids":{"openalex":"https://openalex.org/W6912861407","doi":"https://doi.org/10.5555/3635637.3663059"},"language":"en","primary_location":{"id":"pmh:oai:pure.tue.nl:publications/037d69a0-fcfc-4a88-84c1-0e75c1edb4b5","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/037d69a0-fcfc-4a88-84c1-0e75c1edb4b5","pdf_url":"https://pure.tue.nl/ws/files/332092090/3635637.3663059.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.tue.nl/ws/files/332092090/3635637.3663059.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"WU, Yaoxin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"WU, Yaoxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"FAN, Mingfeng","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"FAN, Mingfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"CAO, Zhiguang","orcid":null},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"CAO, Zhiguang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"GAO, Ruobin","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"GAO, Ruobin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"HOU, Yaqing","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"HOU, Yaqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"SARTORETTI, Guillaume","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"SARTORETTI, Guillaume","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10567","display_name":"Vehicle Routing Optimization Methods","score":0.9025999903678894,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10567","display_name":"Vehicle Routing Optimization Methods","score":0.9025999903678894,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.03689999878406525,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.00839999970048666,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7505000233650208},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5860999822616577},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4226999878883362},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4124999940395355},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.38929998874664307},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.37380000948905945},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3650999963283539},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.3637999892234802}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7505000233650208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718999981880188},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5860999822616577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5195000171661377},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4147999882698059},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3425999879837036},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C123784306","wikidata":"https://www.wikidata.org/wiki/Q944041","display_name":"Vehicle routing problem","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.26489999890327454}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:pure.tue.nl:publications/037d69a0-fcfc-4a88-84c1-0e75c1edb4b5","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/037d69a0-fcfc-4a88-84c1-0e75c1edb4b5","pdf_url":"https://pure.tue.nl/ws/files/332092090/3635637.3663059.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-10328","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/9328","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.5555/3635637.3663059","raw_type":"Conference Proceeding Article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/037d69a0-fcfc-4a88-84c1-0e75c1edb4b5","is_oa":true,"landing_page_url":"https://research.tue.nl/files/332092090/3635637.3663059.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:publications/037d69a0-fcfc-4a88-84c1-0e75c1edb4b5","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/037d69a0-fcfc-4a88-84c1-0e75c1edb4b5","pdf_url":"https://pure.tue.nl/ws/files/332092090/3635637.3663059.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1162322055","display_name":null,"funder_award_id":"DUT22ZD214","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3363435710","display_name":null,"funder_award_id":"DUT21TD107","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5696533889","display_name":null,"funder_award_id":"62372081","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/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6912861407.pdf","grobid_xml":"https://content.openalex.org/works/W6912861407.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"deep":[1,61],"reinforcement":[2,62],"learning":[3,63],"(DRL)":[4],"methods":[5],"for":[6,99],"multi-objective":[7],"vehicle":[8],"routing":[9],"problems":[10],"(MOVRPs)":[11],"typically":[12],"decompose":[13],"an":[14],"MOVRP":[15],"into":[16],"subproblems":[17,83],"with":[18],"respective":[19,107],"preferences":[20],"and":[21,94,168,176],"then":[22],"train":[23],"policies":[24],"to":[25,78,82,105,117,155,161],"solve":[26],"corresponding":[27],"subproblems.":[28,163],"However,":[29],"such":[30],"a":[31,59,68,87,95,112,126],"paradigm":[32],"is":[33,97,179,197],"still":[34],"less":[35],"effective":[36],"in":[37,84],"tackling":[38],"the":[39,47,50,75,91,120,129,137,144,172,183,192],"intricate":[40],"interactions":[41,145],"among":[42],"subproblems,":[43],"thus":[44],"holding":[45],"back":[46],"quality":[48],"of":[49,128,146,158,174],"Pareto":[51],"solutions.":[52,108],"To":[53],"counteract":[54],"this":[55],"limitation,":[56],"we":[57,110,140],"introduce":[58],"collaborative":[60,113],"method.":[64],"We":[65],"first":[66],"propose":[67],"preference-based":[69],"attention":[70],"network":[71],"(PAN)":[72],"that":[73],"allows":[74],"DRL":[76,148],"agents":[77,149],"reason":[79],"out":[80],"solutions":[81,160],"parallel,":[85],"where":[86],"shared":[88],"encoder":[89],"learns":[90],"instance":[92,133],"embedding":[93],"decoder":[96,130],"tailored":[98],"each":[100],"agent":[101],"by":[102,150],"preference":[103],"intervention":[104],"construct":[106],"Then,":[109],"design":[111],"active":[114],"search":[115],"(CAS)":[116],"further":[118],"improve":[119],"solution":[121],"quality,":[122],"which":[123,178],"updates":[124],"only":[125],"part":[127],"parameters":[131],"per":[132],"during":[134],"inference.":[135],"In":[136],"CAS":[138],"process,":[139],"also":[141],"explicitly":[142],"foster":[143],"neighboring":[147],"imitation":[151],"learning,":[152],"empowering":[153],"them":[154],"exchange":[156],"insights":[157],"elite":[159],"similar":[162],"Extensive":[164],"results":[165],"on":[166,182],"random":[167],"benchmark":[169],"instances":[170],"verified":[171],"efficacy":[173],"PAN":[175],"CAS,":[177],"particularly":[180],"pronounced":[181],"configurations":[184],"(i.e.,":[185],"problem":[186],"sizes":[187],"or":[188],"node":[189],"distributions)":[190],"beyond":[191],"training":[193],"ones.":[194],"Our":[195],"code":[196],"available":[198],"at":[199],"https://github.com/marmotlab/PAN-CAS.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}