{"id":"https://openalex.org/W4407838716","doi":"https://doi.org/10.1145/3719208","title":"Retentive Decision Transformer with Adaptive Masking for Reinforcement Learning-Based Recommendation Systems","display_name":"Retentive Decision Transformer with Adaptive Masking for Reinforcement Learning-Based Recommendation Systems","publication_year":2025,"publication_date":"2025-02-21","ids":{"openalex":"https://openalex.org/W4407838716","doi":"https://doi.org/10.1145/3719208"},"language":"en","primary_location":{"id":"doi:10.1145/3719208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719208","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3719208","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100358930","display_name":"Siyu Wang","orcid":"https://orcid.org/0009-0008-8726-5277"},"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":"Siyu Wang","raw_affiliation_strings":["The University of New South Wales, Sydney, Australia","The University of New South Wales, Australia"],"raw_orcid":"https://orcid.org/0009-0008-8726-5277","affiliations":[{"raw_affiliation_string":"The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"The University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057487706","display_name":"Xiaocong Chen","orcid":"https://orcid.org/0000-0002-8849-4943"},"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/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":["CSIRO Data61 Business Unit, Eveleigh, Australia","Data61, CSIRO, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8849-4943","affiliations":[{"raw_affiliation_string":"CSIRO Data61 Business Unit, Eveleigh, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"Data61, CSIRO, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]},{"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/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/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"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":"Lina Yao","raw_affiliation_strings":["CSIRO Data61 Business Unit, Eveleigh, Australia and The University of New South Wales, Sydney, Australia","Data61, CSIRO, Australia and The University of New South Wales, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4149-839X","affiliations":[{"raw_affiliation_string":"CSIRO Data61 Business Unit, Eveleigh, Australia and The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"Data61, CSIRO, Australia and The University of New South Wales, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I31746571","https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.4079,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98191719,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"16","issue":"3","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9948999881744385,"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":0.9948999881744385,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9914000034332275,"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":0.9840999841690063,"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/computer-science","display_name":"Computer science","score":0.8963013291358948},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8552432060241699},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7256288528442383},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4484342932701111},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43977344036102295},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42511945962905884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3817819058895111},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11750957369804382},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08693388104438782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8963013291358948},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8552432060241699},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7256288528442383},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4484342932701111},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43977344036102295},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42511945962905884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3817819058895111},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11750957369804382},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08693388104438782},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3719208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719208","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3719208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719208","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2069065514","https://openalex.org/W2095705004","https://openalex.org/W2788295351","https://openalex.org/W2799544270","https://openalex.org/W2893359107","https://openalex.org/W2950275995","https://openalex.org/W2963367478","https://openalex.org/W2963619374","https://openalex.org/W2963654596","https://openalex.org/W2971196067","https://openalex.org/W2984100107","https://openalex.org/W2994850640","https://openalex.org/W3005071803","https://openalex.org/W3017289192","https://openalex.org/W3065542300","https://openalex.org/W3100260481","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3123348991","https://openalex.org/W3208231292","https://openalex.org/W4214717370","https://openalex.org/W4250482878","https://openalex.org/W4296604485","https://openalex.org/W4318159260","https://openalex.org/W4324312897","https://openalex.org/W4327525152","https://openalex.org/W4383993482","https://openalex.org/W4384644538","https://openalex.org/W4384891727","https://openalex.org/W4387031395","https://openalex.org/W4389524555","https://openalex.org/W4396216288","https://openalex.org/W4401856724","https://openalex.org/W4401863542","https://openalex.org/W6700982323"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","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/W1987513656"],"abstract_inverted_index":{"Reinforcement":[0],"Learning-Based":[1],"Recommender":[2],"Systems":[3],"(RLRS)":[4],"have":[5],"shown":[6],"promise":[7],"across":[8,153],"a":[9,44,98,160],"spectrum":[10],"of":[11,169,191],"applications,":[12],"from":[13],"e-commerce":[14],"platforms":[15],"to":[16,48,88,103,151],"streaming":[17],"services.":[18],"Yet,":[19],"they":[20],"grapple":[21],"with":[22,71,105],"challenges,":[23],"notably":[24],"in":[25,40],"crafting":[26],"reward":[27],"functions":[28],"and":[29,74,184],"harnessing":[30],"large":[31],"pre-existing":[32],"datasets":[33],"within":[34],"the":[35,59,78,106,111,134,148,189],"RL":[36],"framework.":[37],"Recent":[38],"advancements":[39],"offline":[41,100,185],"RLRS":[42,101,112],"provide":[43],"solution":[45],"for":[46],"how":[47],"address":[49],"these":[50],"two":[51],"challenges.":[52],"However,":[53],"existing":[54],"methods":[55,80],"mainly":[56],"rely":[57],"on":[58,142,180],"transformer":[60],"architecture,":[61],"which,":[62],"as":[63,118],"sequence":[64],"lengths":[65],"increase,":[66],"can":[67],"introduce":[68,97],"challenges":[69],"associated":[70],"computational":[72,174],"resources":[73],"training":[75],"costs.":[76],"Additionally,":[77],"prevalent":[79],"employ":[81],"fixed-length":[82],"input":[83,131],"trajectories,":[84],"restricting":[85],"their":[86],"capacity":[87],"capture":[89],"evolving":[90],"user":[91],"preferences.":[92],"In":[93],"this":[94],"study,":[95],"we":[96,158],"new":[99],"method":[102],"deal":[104],"above":[107],"problems.":[108],"We":[109],"reinterpret":[110],"challenge":[113,140],"by":[114],"modeling":[115,168],"sequential":[116],"decision-making":[117],"an":[119,138],"inference":[120,139],"task,":[121],"leveraging":[122],"adaptive":[123,127],"masking":[124],"configurations.":[125],"This":[126],"approach":[128],"selectively":[129],"masks":[130],"tokens,":[132],"transforming":[133],"recommendation":[135],"task":[136],"into":[137],"based":[141],"varying":[143],"token":[144],"subsets,":[145],"thereby":[146],"enhancing":[147,173],"agent\u2019s":[149],"ability":[150],"infer":[152],"diverse":[154],"trajectory":[155],"lengths.":[156],"Furthermore,":[157],"incorporate":[159],"multi-scale":[161],"segmented":[162],"retention":[163],"mechanism":[164],"that":[165],"facilitates":[166],"efficient":[167],"long":[170],"sequences,":[171],"significantly":[172],"efficiency.":[175],"Our":[176],"experimental":[177],"analysis,":[178],"conducted":[179],"both":[181],"online":[182],"simulator":[183],"datasets,":[186],"clearly":[187],"demonstrates":[188],"advantages":[190],"our":[192],"proposed":[193],"method.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}