{"id":"https://openalex.org/W4400947023","doi":"https://doi.org/10.23919/ecc64448.2024.10590895","title":"Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning","display_name":"Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning","publication_year":2024,"publication_date":"2024-06-25","ids":{"openalex":"https://openalex.org/W4400947023","doi":"https://doi.org/10.23919/ecc64448.2024.10590895"},"language":"en","primary_location":{"id":"doi:10.23919/ecc64448.2024.10590895","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc64448.2024.10590895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 European Control Conference (ECC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5108041807","display_name":"Carolin Schmidt","orcid":"https://orcid.org/0009-0006-8183-2846"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Carolin Schmidt","raw_affiliation_strings":["Technical University of Denmark,Department of Technology, Management and Economics,Kongens Lyngby,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Denmark,Department of Technology, Management and Economics,Kongens Lyngby,Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034366030","display_name":"Daniele Gammelli","orcid":"https://orcid.org/0000-0003-1802-4388"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniele Gammelli","raw_affiliation_strings":["Stanford University,Department of Aeronautics and Astronautics,Stanford,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Aeronautics and Astronautics,Stanford,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Francisco Camara Pereira","orcid":null},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Francisco Camara Pereira","raw_affiliation_strings":["Technical University of Denmark,Department of Technology, Management and Economics,Kongens Lyngby,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Denmark,Department of Technology, Management and Economics,Kongens Lyngby,Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078981714","display_name":"Filipe Rodrigues","orcid":"https://orcid.org/0000-0001-6979-6498"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Filipe Rodrigues","raw_affiliation_strings":["Technical University of Denmark,Department of Technology, Management and Economics,Kongens Lyngby,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Denmark,Department of Technology, Management and Economics,Kongens Lyngby,Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8448,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92310974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1399","last_page":"1406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9980999827384949,"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/T12288","display_name":"Optimization and Search Problems","score":0.9977999925613403,"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":0.8509801626205444},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6920421123504639},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5223706364631653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5086515545845032},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36001232266426086}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8509801626205444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920421123504639},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5223706364631653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5086515545845032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36001232266426086}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/ecc64448.2024.10590895","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc64448.2024.10590895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 European Control Conference (ECC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2803952469","https://openalex.org/W2915314538","https://openalex.org/W2963144120","https://openalex.org/W2968116426","https://openalex.org/W2984671888","https://openalex.org/W2990138404","https://openalex.org/W3015295488","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3042585537","https://openalex.org/W3089834075","https://openalex.org/W3114580520","https://openalex.org/W3128328080","https://openalex.org/W3166344325","https://openalex.org/W3184771397","https://openalex.org/W3213037073","https://openalex.org/W4226047880","https://openalex.org/W4287186482","https://openalex.org/W4290943497","https://openalex.org/W4290943640","https://openalex.org/W4291125977","https://openalex.org/W4312403563","https://openalex.org/W4323927473","https://openalex.org/W4360584316","https://openalex.org/W6747473740","https://openalex.org/W6770110395","https://openalex.org/W6779265984","https://openalex.org/W6790767801","https://openalex.org/W6804006238","https://openalex.org/W6853388382"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Autonomous":[0],"Mobility-on-Demand":[1],"(AMoD)":[2],"systems":[3,27,87,127],"are":[4],"an":[5],"evolving":[6],"mode":[7],"of":[8,16,25,69,85,91,176],"transportation":[9,73],"in":[10,53],"which":[11,104],"a":[12,32,45,170],"centrally":[13],"coordinated":[14],"fleet":[15],"self-driving":[17],"vehicles":[18],"dynamically":[19],"serves":[20],"travel":[21],"requests.":[22],"The":[23],"control":[24,84,98,136],"these":[26,77],"is":[28,105,169],"typically":[29],"formulated":[30],"as":[31,44,183],"large":[33],"network":[34],"optimization":[35],"problem,":[36],"and":[37,95,117,153],"reinforcement":[38,93],"learning":[39,62,94,131],"(RL)":[40],"has":[41],"recently":[42],"emerged":[43],"promising":[46,171],"approach":[47],"to":[48,81,108,133],"solve":[49],"the":[50,67,83,89,156,174],"open":[51],"challenges":[52],"this":[54,163],"space.":[55],"Recent":[56],"centralized":[57],"RL":[58,168],"approaches":[59],"focus":[60],"on":[61,122,142],"from":[63,124],"online":[64,145,151],"data,":[65,103],"ignoring":[66],"per-sample-cost":[68],"interactions":[70],"within":[71,179],"real-world":[72,125],"systems.":[74,185],"To":[75],"address":[76],"limitations,":[78],"we":[79],"propose":[80],"formalize":[82],"AMoD":[86,135],"through":[88],"lens":[90],"offline":[92,102,130,167],"learn":[96],"effective":[97],"strategies":[99],"using":[100],"solely":[101],"readily":[106],"available":[107],"current":[109],"mobility":[110,126,184],"operators.":[111],"We":[112],"further":[113],"investigate":[114],"design":[115],"decisions":[116],"provide":[118],"empirical":[119],"evidence":[120],"based":[121],"data":[123],"showing":[128],"how":[129],"allows":[132],"recover":[134],"policies":[137],"that":[138,166],"(i)":[139],"exhibit":[140],"performance":[141],"par":[143],"with":[144],"methods,":[146],"(ii)":[147],"allow":[148],"for":[149,158,173],"sample-efficient":[150],"fine-tuning":[152],"(iii)":[154],"eliminate":[155],"need":[157],"complex":[159],"simulation":[160],"environments.":[161],"Crucially,":[162],"paper":[164],"demonstrates":[165],"paradigm":[172],"application":[175],"RL-based":[177],"solutions":[178],"economically-critical":[180],"systems,":[181],"such":[182]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}