{"id":"https://openalex.org/W4384408011","doi":"https://doi.org/10.1007/s11280-023-01187-7","title":"Intrinsically motivated reinforcement learning based recommendation with counterfactual data augmentation","display_name":"Intrinsically motivated reinforcement learning based recommendation with counterfactual data augmentation","publication_year":2023,"publication_date":"2023-07-15","ids":{"openalex":"https://openalex.org/W4384408011","doi":"https://doi.org/10.1007/s11280-023-01187-7"},"language":"en","primary_location":{"id":"doi:10.1007/s11280-023-01187-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11280-023-01187-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11280-023-01187-7.pdf","source":{"id":"https://openalex.org/S129236917","display_name":"World Wide Web","issn_l":"1386-145X","issn":["1386-145X","1573-1413"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Wide Web","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11280-023-01187-7.pdf","any_repository_has_fulltext":false},"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/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Xiaocong Chen","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Sydney, 2052, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Sydney, 2052, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"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/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, University of New South Wales, Sydney, 2052, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Sydney, 2052, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006514077","display_name":"Lianyong Qi","orcid":"https://orcid.org/0000-0001-9875-9856"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianyong Qi","raw_affiliation_strings":["College of Computer Science and Technology, China University of Petroleum (East China), Dong Ying Shi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, China University of Petroleum (East China), Dong Ying Shi, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092476434","display_name":"Yong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China","College of Computer Science and Technology, China University of Petroleum (East China), Dong Ying Shi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"College of Computer Science and Technology, China University of Petroleum (East China), Dong Ying Shi, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"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":["Data 61, CSIRO, Eveleigh, 2015, NSW, Australia","School of Computer Science and Engineering, University of New South Wales, Sydney, 2052, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data 61, CSIRO, Eveleigh, 2015, NSW, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]},{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Sydney, 2052, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057487706"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":3.4389,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.93447557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"26","issue":"5","first_page":"3253","last_page":"3274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994000196456909,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9854999780654907,"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":0.888635516166687},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.8760294914245605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8697253465652466},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5901927351951599},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5785874724388123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5562731623649597},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5360394716262817},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5174930095672607}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.888635516166687},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8760294914245605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8697253465652466},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5901927351951599},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5785874724388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5562731623649597},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5360394716262817},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5174930095672607},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11280-023-01187-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11280-023-01187-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11280-023-01187-7.pdf","source":{"id":"https://openalex.org/S129236917","display_name":"World Wide Web","issn_l":"1386-145X","issn":["1386-145X","1573-1413"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Wide Web","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11280-023-01187-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11280-023-01187-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11280-023-01187-7.pdf","source":{"id":"https://openalex.org/S129236917","display_name":"World Wide Web","issn_l":"1386-145X","issn":["1386-145X","1573-1413"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Wide Web","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320965","display_name":"University of New South Wales","ror":"https://ror.org/03r8z3t63"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384408011.pdf","grobid_xml":"https://content.openalex.org/works/W4384408011.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W2029236670","https://openalex.org/W2078109946","https://openalex.org/W2099111195","https://openalex.org/W2106469529","https://openalex.org/W2143117649","https://openalex.org/W2145339207","https://openalex.org/W2148986322","https://openalex.org/W2737622740","https://openalex.org/W2787933113","https://openalex.org/W2788295351","https://openalex.org/W2801890059","https://openalex.org/W2902572901","https://openalex.org/W2950275995","https://openalex.org/W2963099939","https://openalex.org/W2963367478","https://openalex.org/W2963440040","https://openalex.org/W2963619374","https://openalex.org/W2963654596","https://openalex.org/W2970971581","https://openalex.org/W2998004401","https://openalex.org/W3017289192","https://openalex.org/W3035106673","https://openalex.org/W3097679710","https://openalex.org/W3102778384","https://openalex.org/W3153754021","https://openalex.org/W3154419237","https://openalex.org/W3154921101","https://openalex.org/W3156939347","https://openalex.org/W3170713142","https://openalex.org/W3200235377","https://openalex.org/W3200556911","https://openalex.org/W3208231292","https://openalex.org/W4284706735","https://openalex.org/W4284712454","https://openalex.org/W4293569092","https://openalex.org/W4318159260","https://openalex.org/W4318823254","https://openalex.org/W4321480051","https://openalex.org/W6600291286","https://openalex.org/W6600864179","https://openalex.org/W6601730711"],"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":{"Abstract":[0],"Deep":[1],"reinforcement":[2,110],"learning":[3,111],"(DRL)":[4],"has":[5],"shown":[6],"promising":[7],"results":[8],"in":[9,14,16,24,95,124,147,180,185],"modeling":[10],"dynamic":[11],"user":[12],"preferences":[13],"RS":[15,27,188],"recent":[17],"literature.":[18],"However,":[19],"training":[20],"a":[21,30,53,106,140],"DRL":[22],"agent":[23,37,84],"the":[25,36,63,67,83,96,116,125,186],"sparse":[26,126,187],"environment":[28,68],"poses":[29],"significant":[31],"challenge.":[32],"This":[33,59],"is":[34,69,78,151],"because":[35],"must":[38],"balance":[39],"between":[40],"exploring":[41],"informative":[42,89,121],"user-item":[43],"interaction":[44,122],"trajectories":[45,49,90,123,132],"and":[46,56,76,91,157],"using":[47],"existing":[48,166],"for":[50],"policy":[51],"learning,":[52],"known":[54],"exploration":[55,75],"exploitation":[57,77],"trade-off.":[58],"trade-off":[60],"greatly":[61],"affects":[62],"recommendation":[64,183],"performance":[65,184],"when":[66],"sparse.":[70],"In":[71],"DRL-based":[72],"RS,":[73],"balancing":[74],"even":[79],"more":[80],"challenging":[81],"as":[82],"needs":[85],"to":[86,119,143],"deeply":[87],"explore":[88,120],"efficiently":[92],"exploit":[93],"them":[94],"context":[97],"of":[98,182],"RS.":[99],"To":[100],"address":[101],"this":[102],"issue,":[103],"we":[104],"propose":[105],"novel":[107],"intrinsically":[108],"motivated":[109],"(IMRL)":[112],"method":[113,176],"that":[114,173],"enhances":[115],"agent\u2019s":[117],"capability":[118],"environment.":[127,189],"We":[128],"further":[129],"enrich":[130],"these":[131],"via":[133],"an":[134],"adaptive":[135],"counterfactual":[136],"augmentation":[137],"strategy":[138],"with":[139],"customised":[141],"threshold":[142],"improve":[144],"their":[145],"efficiency":[146],"exploitation.":[148],"Our":[149],"approach":[150],"evaluated":[152],"on":[153],"six":[154],"offline":[155],"datasets":[156],"three":[158],"online":[159],"simulation":[160],"platforms,":[161],"demonstrating":[162],"its":[163],"superiority":[164],"over":[165],"state-of-the-art":[167],"methods.":[168],"The":[169],"extensive":[170],"experiments":[171],"show":[172],"our":[174],"IMRL":[175],"outperforms":[177],"other":[178],"methods":[179],"terms":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}
