{"id":"https://openalex.org/W4388740239","doi":"https://doi.org/10.1109/tnnls.2023.3329808","title":"Plug-and-Play Model-Agnostic Counterfactual Policy Synthesis for Deep Reinforcement Learning-Based Recommendation","display_name":"Plug-and-Play Model-Agnostic Counterfactual Policy Synthesis for Deep Reinforcement Learning-Based Recommendation","publication_year":2023,"publication_date":"2023-11-16","ids":{"openalex":"https://openalex.org/W4388740239","doi":"https://doi.org/10.1109/tnnls.2023.3329808","pmid":"https://pubmed.ncbi.nlm.nih.gov/37971915"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3329808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3329808","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/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":["School of Computer Science and Engineering, The University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0008-8726-5277","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, The University of New South Wales, Sydney, NSW, 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":["Data61, CSIRO, Eveleigh, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8849-4943","affiliations":[{"raw_affiliation_string":"Data61, CSIRO, Eveleigh, NSW, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021827617","display_name":"Julian McAuley","orcid":"https://orcid.org/0000-0003-0955-7588"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian McAuley","raw_affiliation_strings":["Computer Science Department, University of California at San Diego (UCSD), La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California at San Diego (UCSD), La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089488913","display_name":"Sally Cripps","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sally Cripps","raw_affiliation_strings":["Human Technology Institute, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3207-172X","affiliations":[{"raw_affiliation_string":"Human Technology Institute, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"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":["School of Computer Science and Engineering, The University of New South Wales, Sydney, NSW, Australia","Data61, CSIRO, Eveleigh, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4149-839X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, The University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"Data61, CSIRO, Eveleigh, NSW, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2345,"currency":"USD","value_usd":2345},"apc_paid":null,"fwci":1.3526,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81835625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"36","issue":"1","first_page":"1044","last_page":"1055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9467999935150146,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9467999935150146,"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"}},{"id":"https://openalex.org/T11052","display_name":"Energy Load and Power Forecasting","score":0.9168000221252441,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10603","display_name":"Smart Grid Energy Management","score":0.9092000126838684,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9729767441749573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.827454686164856},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7990147471427917},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7941557168960571},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5680176019668579},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5283342599868774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49787402153015137},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49521294236183167}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9729767441749573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827454686164856},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7990147471427917},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7941557168960571},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5680176019668579},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5283342599868774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49787402153015137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49521294236183167},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3329808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3329808","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37971915","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37971915","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2094837707","https://openalex.org/W2108153239","https://openalex.org/W2116206254","https://openalex.org/W2137063737","https://openalex.org/W2155912844","https://openalex.org/W2219888463","https://openalex.org/W2499227277","https://openalex.org/W2629213068","https://openalex.org/W2744211163","https://openalex.org/W2787933113","https://openalex.org/W2788295351","https://openalex.org/W2809162153","https://openalex.org/W2810953629","https://openalex.org/W2950275995","https://openalex.org/W2963619374","https://openalex.org/W2963654596","https://openalex.org/W2987123286","https://openalex.org/W2996959725","https://openalex.org/W2998004401","https://openalex.org/W3017289192","https://openalex.org/W3034791416","https://openalex.org/W3035404611","https://openalex.org/W3035517717","https://openalex.org/W3035598449","https://openalex.org/W3104591237","https://openalex.org/W3152876231","https://openalex.org/W3153754021","https://openalex.org/W3154419237","https://openalex.org/W3156939347","https://openalex.org/W3195311662","https://openalex.org/W3195913310","https://openalex.org/W3208231292","https://openalex.org/W3209458448","https://openalex.org/W3210547226","https://openalex.org/W4214717370","https://openalex.org/W4224308683","https://openalex.org/W4284712454","https://openalex.org/W6684921986","https://openalex.org/W6695055480","https://openalex.org/W6732837357","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6787532554","https://openalex.org/W6800759600","https://openalex.org/W6864350279"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2066431708","https://openalex.org/W3025615835","https://openalex.org/W4384133558","https://openalex.org/W173210993","https://openalex.org/W2390660599","https://openalex.org/W3003410553","https://openalex.org/W3028847759","https://openalex.org/W2393688264"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,41,88,157],"recommender":[3,22,45,56],"systems":[4],"have":[5],"proved":[6],"the":[7,15,42,49,89,94,115,124,130,140,172,187,201],"potential":[8],"of":[9,44,51,53,117,174,191,203],"reinforcement":[10],"learning":[11,25,105],"(RL)":[12],"to":[13,26,60,80,93,132,134,170],"handle":[14],"dynamic":[16,136],"evolution":[17],"processes":[18],"between":[19],"users":[20],"and":[21,109,152,183,189,196],"systems.":[23,46],"However,":[24],"train":[27],"an":[28,158],"optimal":[29],"RL":[30,204],"agent":[31,164],"is":[32,121],"generally":[33],"impractical":[34],"with":[35,106,129,161],"commonly":[36],"sparse":[37],"user":[38,71],"feedback":[39],"data":[40,73,120,169],"context":[43],"To":[47],"circumvent":[48],"lack":[50],"interaction":[52,72,128],"current":[54,125],"RL-based":[55],"systems,":[57],"we":[58,103],"propose":[59],"learn":[61],"a":[62,113,162],"general":[63],"model-agnostic":[64],"counterfactual":[65,70,76,82,119,168,193],"synthesis":[66,77,116,194],"(MACS)":[67],"policy":[68,78,142,145,195],"for":[69],"augmentation.":[74],"The":[75,176],"aims":[79],"synthesize":[81],"states":[83],"while":[84],"preserving":[85],"significant":[86],"information":[87],"original":[90],"state":[91],"relevant":[92],"user's":[95],"interests,":[96],"building":[97],"upon":[98],"two":[99],"different":[100],"training":[101],"approaches":[102],"designed:":[104],"expert":[107],"demonstrations":[108],"joint":[110],"training.":[111],"As":[112],"result,":[114],"each":[118],"based":[122],"on":[123,179],"recommendation":[126,163,205],"agent's":[127],"environment":[131],"adapt":[133],"users'":[135],"interests.":[137],"We":[138],"integrate":[139],"proposed":[141],"deep":[143],"deterministic":[144],"gradient":[146],"(DDPG),":[147],"soft":[148],"actor":[149],"critic":[150],"(SAC),":[151],"twin":[153],"delayed":[154],"DDPG":[155],"(TD3)":[156],"adaptive":[159],"pipeline":[160],"that":[165,198],"can":[166],"generate":[167],"improve":[171],"performance":[173,202],"recommendation.":[175],"empirical":[177],"results":[178],"both":[180],"online":[181],"simulation":[182],"offline":[184],"datasets":[185],"demonstrate":[186],"effectiveness":[188],"generalization":[190],"our":[192],"verify":[197],"it":[199],"improves":[200],"agents.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}