{"id":"https://openalex.org/W4385764103","doi":"https://doi.org/10.24963/ijcai.2023/796","title":"Reinforcement Learning from Optimization Proxy for Ride-Hailing Vehicle Relocation (Extended Abstract)","display_name":"Reinforcement Learning from Optimization Proxy for Ride-Hailing Vehicle Relocation (Extended Abstract)","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764103","doi":"https://doi.org/10.24963/ijcai.2023/796"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/796","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/796","pdf_url":"https://www.ijcai.org/proceedings/2023/0796.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0796.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024300696","display_name":"Enpeng Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Enpeng Yuan","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362717","display_name":"Wenbo Chen","orcid":"https://orcid.org/0000-0002-5712-6101"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenbo Chen","raw_affiliation_strings":["Georgia Institute of Technolody","Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technolody","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035808622","display_name":"Pascal Van Hentenryck","orcid":"https://orcid.org/0000-0001-7085-9994"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pascal Van Hentenryck","raw_affiliation_strings":["Georgia Institute of Technolody","Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technolody","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024300696"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08906896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6990","last_page":"6994"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.9998999834060669,"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":0.9998999834060669,"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/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10524","display_name":"Traffic control and management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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":0.9281682968139648},{"id":"https://openalex.org/keywords/relocation","display_name":"Relocation","score":0.8350806832313538},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7430789470672607},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.5543540716171265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3859935700893402},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.33692416548728943},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24828526377677917},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15598216652870178}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9281682968139648},{"id":"https://openalex.org/C2779019381","wikidata":"https://www.wikidata.org/wiki/Q3499564","display_name":"Relocation","level":2,"score":0.8350806832313538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430789470672607},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.5543540716171265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3859935700893402},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.33692416548728943},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24828526377677917},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15598216652870178},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/796","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/796","pdf_url":"https://www.ijcai.org/proceedings/2023/0796.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/796","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/796","pdf_url":"https://www.ijcai.org/proceedings/2023/0796.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G3190049731","display_name":null,"funder_award_id":"1854684","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5986150752","display_name":null,"funder_award_id":"2112533","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764103.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2332425246","https://openalex.org/W2569460227","https://openalex.org/W2605887650","https://openalex.org/W2757649114","https://openalex.org/W2760107175","https://openalex.org/W2789200469","https://openalex.org/W2790769276","https://openalex.org/W2798644178","https://openalex.org/W2963144120","https://openalex.org/W2963679997","https://openalex.org/W2964169391","https://openalex.org/W2990057693","https://openalex.org/W3013884527","https://openalex.org/W3015295488","https://openalex.org/W3035525384","https://openalex.org/W3136804670","https://openalex.org/W3184771397","https://openalex.org/W3206820790","https://openalex.org/W4310121896","https://openalex.org/W6749576355"],"related_works":["https://openalex.org/W2046732476","https://openalex.org/W2486027828","https://openalex.org/W2034964907","https://openalex.org/W2380877425","https://openalex.org/W2147260044","https://openalex.org/W2365744358","https://openalex.org/W2330526172","https://openalex.org/W2066619073","https://openalex.org/W2386505781","https://openalex.org/W2992703792"],"abstract_inverted_index":{"Idle":[0],"vehicle":[1],"relocation":[2,145],"is":[3,53,114],"crucial":[4],"for":[5,48],"addressing":[6],"demand-supply":[7],"imbalance":[8],"that":[9,73,94,138],"frequently":[10],"arises":[11],"in":[12,36],"the":[13,75,78,101,132,139,144,153],"ride-hailing":[14],"system.":[15],"Current":[16],"mainstream":[17],"methodologies":[18],"-":[19,24],"optimization":[20,88,97,127,154],"and":[21,38,57,99,118,120,147],"reinforcement":[22,104,158],"learning":[23,52,159],"suffer":[25],"from":[26,109],"obvious":[27],"computational":[28,49,165],"drawbacks.":[29,83],"Optimization":[30,110],"models":[31],"need":[32],"to":[33,55,60,116,152,161,164],"be":[34],"solved":[35],"real-time":[37],"often":[39,58],"trade":[40],"off":[41],"model":[42,93],"fidelity":[43],"(hence":[44],"quality":[45],"of":[46,77],"solutions)":[47],"efficiency.":[50],"Reinforcement":[51,107],"expensive":[54],"train":[56,117],"struggles":[59],"achieve":[61],"coordination":[62],"among":[63],"a":[64,70,91],"large":[65],"fleet.":[66],"This":[67,106],"paper":[68],"designs":[69],"hybrid":[71],"approach":[72,113,141],"leverages":[74],"strengths":[76],"two":[79],"while":[80,156],"overcoming":[81],"their":[82],"Specifically,":[84],"it":[85],"trains":[86],"an":[87,96],"proxy,":[89],"i.e.,":[90],"machine-learning":[92],"approximates":[95],"model,":[98,155],"refines":[100],"proxy":[102],"with":[103],"learning.":[105],"Learning":[108],"Proxy":[111],"(RLOP)":[112],"efficient":[115],"deploy,":[119],"achieves":[121],"better":[122],"results":[123],"than":[124],"RL":[125],"or":[126],"alone.":[128],"Numerical":[129],"experiments":[130],"on":[131],"New":[133],"York":[134],"City":[135],"dataset":[136],"show":[137],"RLOP":[140],"reduces":[142],"both":[143],"costs":[146],"computation":[148],"time":[149],"significantly":[150],"compared":[151],"pure":[157],"fails":[160],"converge":[162],"due":[163],"complexity.":[166]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}