{"id":"https://openalex.org/W7167888733","doi":"https://doi.org/10.1145/3805712.3809626","title":"Advantage-Conditioned Flow Policy for Offline Reinforcement Learning in Recommendation","display_name":"Advantage-Conditioned Flow Policy for Offline Reinforcement Learning in Recommendation","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167888733","doi":"https://doi.org/10.1145/3805712.3809626"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809626","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809626","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809626","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057487706","display_name":"Xiaocong Chen","orcid":"https://orcid.org/0000-0002-8849-4943"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaocong Chen","raw_affiliation_strings":["Data 61, CSIRO, Eveleigh, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8849-4943","affiliations":[{"raw_affiliation_string":"Data 61, CSIRO, Eveleigh, NSW, Australia","institution_ids":["https://openalex.org/I42894916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358930","display_name":"Siyu Wang","orcid":"https://orcid.org/0009-0008-8726-5277"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Siyu Wang","raw_affiliation_strings":["Macquarie University, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0008-8726-5277","affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["The University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4149-839X","affiliations":[{"raw_affiliation_string":"The University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93825421,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"179","last_page":"189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.7824000120162964,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.7824000120162964,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.027899999171495438,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.027499999850988388,"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":0.7077000141143799},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5982000231742859},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.5676000118255615},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4821000099182129},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4747999906539917},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4564000070095062},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.42669999599456787},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.40299999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764999866485596},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7077000141143799},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6176999807357788},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5982000231742859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5706999897956848},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5676000118255615},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C2779136372","wikidata":"https://www.wikidata.org/wiki/Q10283002","display_name":"Information flow","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809626","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809626","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809626","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809626","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5355851054191589,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2020631728","https://openalex.org/W2787933113","https://openalex.org/W2799544270","https://openalex.org/W2963085847","https://openalex.org/W2963654596","https://openalex.org/W4288083766","https://openalex.org/W4292419518","https://openalex.org/W4292423901","https://openalex.org/W4318159260","https://openalex.org/W4324312897","https://openalex.org/W4384891727","https://openalex.org/W4400528644","https://openalex.org/W4400528915","https://openalex.org/W4401863542","https://openalex.org/W4403577344","https://openalex.org/W4407838716","https://openalex.org/W4409657161","https://openalex.org/W4412396234","https://openalex.org/W4416016501","https://openalex.org/W4416078509","https://openalex.org/W7133233095"],"related_works":[],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"is":[4,28],"a":[5,35,44,49,87,109,144,184],"useful":[6],"approach":[7],"for":[8,85,141],"recommender":[9],"systems":[10],"because":[11],"it":[12,100],"can":[13,68,177],"optimize":[14],"long-term":[15],"user":[16,33,36],"feedback":[17],"from":[18,127,179],"logged":[19,116],"interaction":[20],"data":[21],"without":[22],"online":[23,195],"exploration.":[24],"A":[25],"key":[26],"challenge":[27],"the":[29,115,128,149,153,168,180],"multi-modal":[30],"nature":[31],"of":[32,167],"preferences:":[34],"may":[37],"like":[38],"several":[39],"unrelated":[40],"item":[41],"types,":[42],"so":[43,172],"unimodal":[45],"policy":[46,97,138,150],"(for":[47],"example,":[48],"Gaussian)":[50],"tends":[51],"to":[52,113,152,161],"average":[53],"across":[54],"modes":[55],"and":[56,98,132,143,164,193],"generate":[57],"actions":[58,125],"that":[59,92,147,173,199],"do":[60],"not":[61],"match":[62],"any":[63],"interest.":[64],"Recent":[65],"diffusion-based":[66],"policies":[67],"model":[69,112],"complex":[70],"preference":[71],"distributions,":[72],"but":[73],"they":[74],"often":[75],"require":[76],"many":[77],"denoising":[78],"steps.":[79],"We":[80,156],"propose":[81],"PerfRec":[82,106,200],"(Preference-aware":[83],"Flow":[84],"Recommendation),":[86],"flow-matching":[88],"offline":[89,206],"RL":[90,207],"framework":[91],"learns":[93],"an":[94,102,135],"expressive":[95],"behavioral":[96],"distills":[99],"into":[101],"efficient":[103],"one-step":[104,137],"policy.":[105,155],"(i)":[107],"trains":[108,120,134],"conditional":[110],"flow":[111,130,154],"clone":[114],"action":[117,170],"distribution,":[118,171],"(ii)":[119],"twin":[121],"Q-networks":[122],"using":[123],"next":[124],"sampled":[126],"learned":[129],"policy,":[131],"(iii)":[133],"advantage-conditioned":[136],"with":[139,183],"Q-guidance":[140],"improvement":[142],"distillation":[145],"loss":[146],"keeps":[148],"close":[151],"use":[157],"binary":[158],"advantage":[159],"conditioning":[160],"separate":[162],"high-advantage":[163,181],"low-advantage":[165],"regions":[166],"flow-induced":[169],"at":[174],"inference":[175],"we":[176],"sample":[178],"mode":[182],"single":[185],"forward":[186],"pass.":[187],"Experiments":[188],"on":[189],"five":[190],"benchmark":[191],"datasets":[192],"one":[194],"simulation":[196],"platform":[197],"show":[198],"improves":[201],"recommendation":[202],"performance":[203],"over":[204],"strong":[205],"baselines.":[208]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-11T00:00:00"}