{"id":"https://openalex.org/W4403577367","doi":"https://doi.org/10.1145/3627673.3680108","title":"RL-ISLAP: A Reinforcement Learning Framework for Industrial-Scale Linear Assignment Problems at Alipay","display_name":"RL-ISLAP: A Reinforcement Learning Framework for Industrial-Scale Linear Assignment Problems at Alipay","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403577367","doi":"https://doi.org/10.1145/3627673.3680108"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3680108","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3680108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","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/A5010502454","display_name":"Hanjie Li","orcid":"https://orcid.org/0000-0003-4857-6650"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanjie Li","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103608046","display_name":"Yue Ning","orcid":"https://orcid.org/0000-0002-2314-0159"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Ning","raw_affiliation_strings":["Independent Researcher, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033234818","display_name":"Yang Bao","orcid":"https://orcid.org/0009-0005-9419-8330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Bao","raw_affiliation_strings":["Independent Researcher, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330875","display_name":"Changsheng Li","orcid":"https://orcid.org/0000-0001-9789-7632"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Li","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027833066","display_name":"Binhuan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boxiao Chen","raw_affiliation_strings":["Independent Researcher, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103185953","display_name":"Xingyu Lu","orcid":"https://orcid.org/0009-0002-8493-7839"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingyu Lu","raw_affiliation_strings":["Independent Researcher, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030900096","display_name":"Ye Yuan","orcid":"https://orcid.org/0000-0002-6282-6057"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Yuan","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054991337","display_name":"Guoren Wang","orcid":"https://orcid.org/0000-0002-0181-8379"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoren Wang","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5010502454"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26396073,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4661","last_page":"4668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9939000010490417,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9939000010490417,"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/T12288","display_name":"Optimization and Search Problems","score":0.9911999702453613,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9821000099182129,"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":0.827384352684021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6161990165710449},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5917149186134338},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39052078127861023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38716185092926025},{"id":"https://openalex.org/keywords/industrial-engineering","display_name":"Industrial engineering","score":0.34566718339920044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2025684118270874},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20194151997566223},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.058589428663253784}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.827384352684021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6161990165710449},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5917149186134338},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39052078127861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38716185092926025},{"id":"https://openalex.org/C13736549","wikidata":"https://www.wikidata.org/wiki/Q4489420","display_name":"Industrial engineering","level":1,"score":0.34566718339920044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2025684118270874},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20194151997566223},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.058589428663253784},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3680108","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3680108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","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":21,"referenced_works":["https://openalex.org/W149946109","https://openalex.org/W1524324710","https://openalex.org/W1977229458","https://openalex.org/W1985482879","https://openalex.org/W2049967755","https://openalex.org/W2079261074","https://openalex.org/W2277973662","https://openalex.org/W2592843051","https://openalex.org/W2769646558","https://openalex.org/W2902719825","https://openalex.org/W2964002344","https://openalex.org/W3095180254","https://openalex.org/W3101798601","https://openalex.org/W3168933125","https://openalex.org/W3185099629","https://openalex.org/W4282970521","https://openalex.org/W4285601644","https://openalex.org/W4286484206","https://openalex.org/W4287122887","https://openalex.org/W4385567739","https://openalex.org/W4394828208"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Industrial-scale":[0],"linear":[1],"assignment":[2],"problems":[3,26],"(LAPs)":[4],"are":[5,29,56],"frequently":[6],"encountered":[7],"in":[8,104,129,166,190],"various":[9],"industrial":[10],"scenarios,":[11],"e.g.,":[12],"asset":[13],"allocation":[14],"within":[15],"the":[16,52,80,99,130,148,157,193,198],"domain":[17],"of":[18,151,164,179,187,192],"credit":[19],"management.":[20],"However,":[21],"optimization":[22],"algorithms":[23],"for":[24,73,83,107,118],"such":[25,108],"(e.g.,":[27],"PJ-ADMM)":[28],"highly":[30],"sensitive":[31],"to":[32,45,94,114,126,143,155,161,176,197],"hyper-parameters.":[33],"Existing":[34],"solving":[35,131,201],"systems":[36],"rely":[37],"on":[38,134],"empirical":[39,205],"parameter":[40,54,206],"selection,":[41],"which":[42],"is":[43,141],"challenging":[44],"achieve":[46],"convergence":[47],"and":[48,68,90,121],"extremely":[49],"time-consuming.":[50],"Additionally,":[51],"resulting":[53],"rules":[55],"often":[57],"inefficient.":[58],"To":[59],"alleviate":[60],"this":[61],"issue,":[62],"we":[63,110],"propose":[64],"RL-ISLAP,":[65],"an":[66],"efficient":[67],"lightweight":[69],"Reinforcement":[70],"Learning":[71],"framework":[72],"Industrial-Scale":[74],"Linear":[75],"Assignment":[76],"Problems.":[77],"We":[78],"formulate":[79],"hyper-parameter":[81,159],"selection":[82],"PJ-ADMM":[84],"as":[85],"a":[86,123,162],"sequential":[87],"decision":[88,180],"problem":[89],"leverage":[91],"reinforcement":[92],"learning":[93,105],"enhance":[95],"its":[96],"convergence.":[97],"Addressing":[98],"sparse":[100],"reward":[101],"challenge":[102],"inherent":[103],"policies":[106],"problems,":[109],"devise":[111],"auxiliary":[112],"rewards":[113],"provide":[115],"dense":[116],"signals":[117],"policy":[119,160],"optimization,":[120],"present":[122],"rollback":[124],"mechanism":[125],"prevent":[127],"divergence":[128],"process.":[132],"Experiments":[133],"OR-Library":[135],"benchmark":[136],"demonstrate":[137],"that":[138],"our":[139,182],"method":[140],"competitive":[142],"SOTA":[144,199],"stand-alone":[145],"solvers.":[146],"Furthermore,":[147],"scale-independent":[149],"design":[150],"observations":[152],"enables":[153],"us":[154],"transfer":[156],"acquired":[158],"scenario":[163],"LAPs":[165,173],"varying":[167],"scales.":[168],"On":[169],"two":[170],"real-world":[171],"industrial-scale":[172],"with":[174],"up":[175],"10":[177],"millions":[178],"variables,":[181],"proposed":[183],"RL-ISLAP":[184],"achieves":[185],"solutions":[186],"comparable":[188],"quality":[189],"2/3":[191],"time":[194],"when":[195],"compared":[196],"distributed":[200],"system":[202],"employing":[203],"fine-tuned":[204],"rules.":[207]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}