{"id":"https://openalex.org/W4401863522","doi":"https://doi.org/10.1145/3637528.3671823","title":"Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing","display_name":"Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863522","doi":"https://doi.org/10.1145/3637528.3671823"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671823","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671823","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671823","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100981077","display_name":"Xinbo Zhao","orcid":"https://orcid.org/0009-0000-3370-7828"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinbo Zhao","raw_affiliation_strings":["Binghamton University, Binghamton, NY, USA"],"raw_orcid":"https://orcid.org/0009-0000-3370-7828","affiliations":[{"raw_affiliation_string":"Binghamton University, Binghamton, NY, USA","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074277827","display_name":"Yingxue Zhang","orcid":"https://orcid.org/0000-0002-0947-1875"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingxue Zhang","raw_affiliation_strings":["Binghamton University, Binghamton, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-0947-1875","affiliations":[{"raw_affiliation_string":"Binghamton University, Binghamton, NY, USA","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327554","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0003-0289-1452"},"institutions":[{"id":"https://openalex.org/I26538001","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42","country_code":"US","type":"education","lineage":["https://openalex.org/I26538001"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["San Diego State University, San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0289-1452","affiliations":[{"raw_affiliation_string":"San Diego State University, San Diego, CA, USA","institution_ids":["https://openalex.org/I26538001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051976513","display_name":"Yu Yang","orcid":"https://orcid.org/0000-0003-1627-5503"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Yang","raw_affiliation_strings":["Lehigh University, Bethlehem, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1627-5503","affiliations":[{"raw_affiliation_string":"Lehigh University, Bethlehem, PA, USA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049041437","display_name":"Yiqun Xie","orcid":"https://orcid.org/0000-0002-6439-1333"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiqun Xie","raw_affiliation_strings":["University of Maryland, College Park, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-6439-1333","affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630059","display_name":"Yanhua Li","orcid":"https://orcid.org/0000-0001-8972-503X"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanhua Li","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8972-503X","affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106731907","display_name":"Jun Luo","orcid":"https://orcid.org/0000-0002-2032-0381"},"institutions":[{"id":"https://openalex.org/I4210131801","display_name":"Hong Kong R&D Centre for Logistics and Supply Chain Management Enabling Technologies","ror":"https://ror.org/03nm59d75","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210131801"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Luo","raw_affiliation_strings":["Logistics and Supply Chain MultiTech R&D Centre, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-2032-0381","affiliations":[{"raw_affiliation_string":"Logistics and Supply Chain MultiTech R&D Centre, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I4210131801"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0668,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78316577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4512","last_page":"4523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9922000169754028,"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":0.9922000169754028,"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/T10524","display_name":"Traffic control and management","score":0.9873999953269958,"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"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9577999711036682,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8308045864105225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7629600167274475},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6558926105499268},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4364749789237976},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39731231331825256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3756747245788574},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11455556750297546},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08521866798400879},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06533285975456238}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8308045864105225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7629600167274475},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6558926105499268},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4364749789237976},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39731231331825256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3756747245788574},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11455556750297546},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08521866798400879},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06533285975456238},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671823","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671823","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3637528.3671823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671823","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671823","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401863522.pdf"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2096733369","https://openalex.org/W2268617045","https://openalex.org/W2914304175","https://openalex.org/W3081056513","https://openalex.org/W4212774754","https://openalex.org/W4234250081","https://openalex.org/W4365394967"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W3196817267"],"abstract_inverted_index":{"Enhancing":[0],"diverse":[1],"human":[2,38,111],"decision-making":[3,214],"processes":[4],"in":[5,93,185,211],"an":[6],"urban":[7,39,47,96,189,213],"environment":[8],"is":[9,30,171],"a":[10,31,74,94,140,150,158,162,186],"critical":[11],"issue":[12],"across":[13],"various":[14],"applications,":[15],"including":[16],"ride-sharing":[17],"vehicle":[18],"dispatching,":[19],"public":[20],"transportation":[21],"management,":[22],"and":[23,36,60,63,91,116],"autonomous":[24],"driving.":[25],"Offline":[26,76],"reinforcement":[27],"learning":[28],"(RL)":[29],"promising":[32],"approach":[33],"to":[34,205,222],"learn":[35],"optimize":[37],"strategies":[40],"(or":[41],"policies)":[42],"from":[43],"pre-collected":[44],"human-generated":[45],"spatial-temporal":[46],"data.":[48],"However,":[49],"standard":[50],"offline":[51,144],"RL":[52,145,175],"faces":[53],"two":[54],"significant":[55,202],"challenges:":[56],"(1)":[57],"data":[58,61,89,118,123,132],"scarcity":[59,90],"heterogeneity,":[62],"(2)":[64],"distributional":[65],"shift.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"introduce":[71],"MODA":[72,84,138,200],"-":[73],"Multi-Task":[75],"Reinforcement":[77],"Learning":[78],"with":[79,127,161],"Contrastive":[80,99],"Data":[81,100],"Sharing":[82,101],"approach.":[83],"addresses":[85],"the":[86,128,168,192,223],"challenges":[87],"of":[88,110,194],"heterogeneity":[92],"multi-task":[95,143,188],"setting":[97,190],"through":[98],"among":[102],"tasks.":[103],"This":[104,147],"technique":[105],"involves":[106],"extracting":[107],"latent":[108],"representations":[109,126],"behaviors":[112],"by":[113,156],"contrasting":[114],"positive":[115],"negative":[117],"pairs.":[119],"It":[120],"then":[121],"shares":[122],"presenting":[124],"similar":[125],"target":[129],"task,":[130],"facilitating":[131],"augmentation":[133],"for":[134],"each":[135],"task.":[136],"Moreover,":[137],"develops":[139],"novel":[141],"model-based":[142],"algorithm.":[146],"algorithm":[148,178],"constructs":[149],"robust":[151,169],"Markov":[152],"Decision":[153],"Process":[154],"(MDP)":[155],"integrating":[157],"dynamics":[159],"model":[160],"Generative":[163],"Adversarial":[164],"Network":[165],"(GAN).":[166],"Once":[167],"MDP":[170],"established,":[172],"any":[173],"online":[174],"or":[176],"planning":[177],"can":[179],"be":[180],"applied.":[181],"Extensive":[182],"experiments":[183],"conducted":[184],"real-world":[187],"validate":[191],"effectiveness":[193],"MODA.":[195],"The":[196],"results":[197],"demonstrate":[198],"that":[199],"exhibits":[201],"improvements":[203],"compared":[204],"state-of-the-art":[206],"baselines,":[207],"showcasing":[208],"its":[209],"capability":[210],"advancing":[212],"processes.":[215],"We":[216],"also":[217],"made":[218],"our":[219],"code":[220],"available":[221],"research":[224],"community.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}