{"id":"https://openalex.org/W4412377077","doi":"https://doi.org/10.1145/3726302.3729942","title":"DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward","display_name":"DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377077","doi":"https://doi.org/10.1145/3726302.3729942"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3729942","doi":"https://doi.org/10.1145/3726302.3729942","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729942","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729942","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729942","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100388218","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0002-7731-0301","observed_orcids":["https://orcid.org/0000-0002-7731-0301"]},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane, Australia and CSIRO DATA 61, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2976-7972","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane, Australia and CSIRO DATA 61, Brisbane, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005674414","display_name":"Ruihong Qiu","orcid":"https://orcid.org/0000-0001-8349-6475","observed_orcids":["https://orcid.org/0000-0001-8349-6475"]},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ruihong Qiu","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8349-6475","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003178925","display_name":"Xuwei Xu","orcid":"https://orcid.org/0000-0003-3434-7451","observed_orcids":["https://orcid.org/0000-0003-3434-7451"]},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuwei Xu","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3434-7451","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050347","display_name":"Jiajun Liu","orcid":"https://orcid.org/0000-0002-5301-8314","observed_orcids":["https://orcid.org/0000-0002-5301-8314","https://orcid.org/0009-0002-0924-8283","https://orcid.org/0009-0004-3904-6564"]},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]},{"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":"Jiajun Liu","raw_affiliation_strings":["CSIRO DATA61, Brisbane, Australia and The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8160-1796","affiliations":[{"raw_affiliation_string":"CSIRO DATA61, Brisbane, Australia and The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I165143802","https://openalex.org/I42894916"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100350745","display_name":"Sen Wang","orcid":"https://orcid.org/0000-0002-5414-8276","observed_orcids":["https://orcid.org/0000-0002-5414-8276","https://orcid.org/0009-0004-2853-794X","https://orcid.org/0000-0002-1012-8900"]},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sen Wang","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5414-8276","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5315,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93113321,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2192","last_page":"2202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9970999956130981,"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":0.9970999956130981,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0020000000949949026,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.9319999814033508},{"id":"https://openalex.org/keywords/recommender-systems","display_name":"recommender systems","score":0.9639999866485596},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.7910000085830688},{"id":"https://openalex.org/keywords/reward-estimation","display_name":"reward estimation","score":0.6000000238418579},{"id":"https://openalex.org/keywords/uncertainty-estimation","display_name":"uncertainty estimation","score":0.5619999766349792}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8319029808044434},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8237597942352295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610187530517578},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6968402862548828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43124663829803467},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3780919313430786},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3726302.3729942","doi":"https://doi.org/10.1145/3726302.3729942","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729942","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729942","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.07257","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07257","pdf_url":"https://arxiv.org/pdf/2505.07257","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.07257","doi":"https://doi.org/10.48550/arxiv.2505.07257","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.07257","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3726302.3729942","doi":"https://doi.org/10.1145/3726302.3729942","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729942","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729942","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.46000000834465027}],"study_designs":[],"awards":[{"id":"https://openalex.org/G3535031997","display_name":null,"funder_award_id":"DE200101610,DE250100919,CE200100025","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320320386","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377077.pdf","grobid_xml":"https://content.openalex.org/works/W4412377077.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2020631728","https://openalex.org/W2251567929","https://openalex.org/W2747956544","https://openalex.org/W2797234205","https://openalex.org/W2963367478","https://openalex.org/W2963619374","https://openalex.org/W2982210816","https://openalex.org/W3007094061","https://openalex.org/W3034853385","https://openalex.org/W3035084859","https://openalex.org/W3038719422","https://openalex.org/W3049342604","https://openalex.org/W3089173487","https://openalex.org/W3103141630","https://openalex.org/W4214717370","https://openalex.org/W4280616270","https://openalex.org/W4308080451","https://openalex.org/W4385567603","https://openalex.org/W4387800505","https://openalex.org/W4396723092","https://openalex.org/W4396734333","https://openalex.org/W4400528915","https://openalex.org/W4403577822","https://openalex.org/W4409158136","https://openalex.org/W6600018615","https://openalex.org/W6600050674","https://openalex.org/W6600281463","https://openalex.org/W6600553734","https://openalex.org/W6600731417"],"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":{"Model-based":[0],"offline":[1,35],"reinforcement":[2],"learning":[3,17],"(RL)":[4],"has":[5],"emerged":[6],"as":[7,58],"a":[8,90,108],"promising":[9],"approach":[10],"for":[11,136],"recommender":[12,124],"systems,":[13],"enabling":[14],"effective":[15],"policy":[16,66],"by":[18,116],"interacting":[19],"with":[20,159],"frozen":[21],"world":[22,30,99],"models.":[23],"However,":[24],"the":[25,82,123,141,145,149,170],"reward":[26,56,134,138],"functions":[27,57],"in":[28,48],"these":[29,85,129],"models,":[31],"trained":[32],"on":[33,165],"sparse":[34],"logs,":[36],"often":[37],"suffer":[38],"from":[39,128],"inaccuracies.":[40,86],"Specifically,":[41],"existing":[42],"methods":[43],"face":[44],"two":[45],"major":[46],"limitations":[47],"addressing":[49],"this":[50,88,183],"challenge:":[51],"(1)":[52],"deterministic":[53],"use":[54],"of":[55,84,144,152,173],"static":[59,70],"look-up":[60],"tables,":[61],"which":[62],"propagates":[63],"inaccuracies":[64],"during":[65],"learning,":[67],"and":[68,80,119,131],"(2)":[69],"uncertainty":[71,154],"designs":[72],"that":[73,122],"fail":[74],"to":[75,96,101,112,156],"effectively":[76],"capture":[77],"decision":[78],"risks":[79],"mitigate":[81],"impact":[83],"In":[87],"work,":[89],"dual-agent":[91],"framework,":[92],"DARLR,":[93,174],"is":[94,110,180],"proposed":[95],"dynamically":[97],"update":[98],"models":[100],"enhance":[102],"recommendation":[103,161],"policies.":[104],"To":[105],"achieve":[106],"this,":[107],"selector":[109],"introduced":[111],"identify":[113],"reference":[114],"users":[115,130,147],"balancing":[117],"similarity":[118],"diversity":[120],"so":[121],"can":[125],"aggregate":[126],"information":[127],"iteratively":[132],"refine":[133],"estimations":[135],"dynamic":[137,150],"shaping.":[139],"Further,":[140],"statistical":[142],"features":[143],"selected":[146],"guide":[148],"adaptation":[151],"an":[153],"penalty":[155],"better":[157],"align":[158],"evolving":[160],"requirements.":[162],"Extensive":[163],"experiments":[164],"four":[166],"benchmark":[167],"datasets":[168],"demonstrate":[169],"superior":[171],"performance":[172],"validating":[175],"its":[176],"effectiveness.":[177],"The":[178],"code":[179],"available":[181],"at":[182],"address.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-15T10:00:46.086208","created_date":"2025-10-10T00:00:00"}