{"id":"https://openalex.org/W4403577344","doi":"https://doi.org/10.1145/3627673.3679674","title":"On Causally Disentangled State Representation Learning for Reinforcement Learning based Recommender Systems","display_name":"On Causally Disentangled State Representation Learning for Reinforcement Learning based Recommender Systems","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403577344","doi":"https://doi.org/10.1145/3627673.3679674"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679674","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679674","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627673.3679674?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3627673.3679674?download=true","any_repository_has_fulltext":null},"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"],"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"]}]},{"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, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8849-4943","affiliations":[{"raw_affiliation_string":"Data61,CSIRO, Eveleigh, 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":["Data61,CSIRO & The University of New South Wales, Eveleigh, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4149-839X","affiliations":[{"raw_affiliation_string":"Data61,CSIRO & The University of New South Wales, Eveleigh, 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":2.5237,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90888652,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2390","last_page":"2399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9973999857902527,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9934999942779541,"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":0.8502762913703918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8115869164466858},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7845272421836853},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6077700257301331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5431373119354248},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5187807083129883},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.510735034942627},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49743178486824036},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.055840104818344116}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8502762913703918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115869164466858},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7845272421836853},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6077700257301331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5431373119354248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5187807083129883},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.510735034942627},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49743178486824036},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.055840104818344116},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679674","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679674","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627673.3679674?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3627673.3679674","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679674","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627673.3679674?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403577344.pdf","grobid_xml":"https://content.openalex.org/works/W4403577344.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2137063737","https://openalex.org/W2629213068","https://openalex.org/W2787666871","https://openalex.org/W2788295351","https://openalex.org/W2801890059","https://openalex.org/W2809162153","https://openalex.org/W2911319979","https://openalex.org/W2950275995","https://openalex.org/W2963619374","https://openalex.org/W2963654596","https://openalex.org/W2998004401","https://openalex.org/W3017289192","https://openalex.org/W3020831971","https://openalex.org/W3035404611","https://openalex.org/W3040094401","https://openalex.org/W3102778384","https://openalex.org/W3103310105","https://openalex.org/W3123348991","https://openalex.org/W3152876231","https://openalex.org/W3154419237","https://openalex.org/W3156939347","https://openalex.org/W3195311662","https://openalex.org/W3195913310","https://openalex.org/W3208231292","https://openalex.org/W3210519732","https://openalex.org/W4224308683","https://openalex.org/W4318159260","https://openalex.org/W4384408011","https://openalex.org/W4388740239"],"related_works":["https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W3197542405","https://openalex.org/W2056712470","https://openalex.org/W3125580266","https://openalex.org/W4317039510","https://openalex.org/W4238861846","https://openalex.org/W790944756"],"abstract_inverted_index":{"In":[0],"Reinforcement":[1],"Learning-based":[2],"Recommender":[3],"Systems":[4],"(RLRS),":[5],"the":[6,29,36,44,53,60,81,96,126,130,140,152,162,172,182,188],"complexity":[7],"and":[8,17,50,83,102,143],"dynamism":[9],"of":[10,28,47,154,161,174,181,190],"user":[11,48],"interactions":[12],"often":[13],"result":[14],"in":[15,34,89],"high-dimensional":[16,144],"noisy":[18],"state":[19,30,82,137,145,169,184],"spaces,":[20],"making":[21,110,159],"it":[22],"challenging":[23],"to":[24,56],"discern":[25],"which":[26,106],"aspects":[27],"are":[31,107],"truly":[32],"influential":[33],"driving":[35],"decision-making":[37,65],"process.":[38],"This":[39],"issue":[40],"is":[41],"exacerbated":[42],"by":[43,158],"evolving":[45],"nature":[46],"preferences":[49],"behaviors,":[51],"requiring":[52],"recommender":[54],"system":[55],"adaptively":[57],"focus":[58],"on":[59,94],"most":[61],"relevant":[62],"information":[63],"for":[64,79,109,151],"while":[66],"preserving":[67],"generaliability.":[68],"To":[69],"tackle":[70],"this":[71],"problem,":[72],"we":[73,118,166],"introduce":[74],"an":[75],"innovative":[76],"causal":[77,127,164],"approach":[78,192],"decomposing":[80],"extracting":[84],"Causal-InDispensable":[85],"State":[86,99],"Representations":[87],"(CIDS)":[88],"RLRS.":[90],"Our":[91],"method":[92,198],"concentrates":[93],"identifying":[95],"Directly":[97],"Action-Influenced":[98],"Variables":[100],"(DAIS)":[101],"Action-Influence":[103],"Ancestors":[104],"(AIA),":[105],"essential":[108],"effective":[111],"recommendations.":[112],"By":[113],"leveraging":[114],"conditional":[115],"mutual":[116],"information,":[117],"develop":[119],"a":[120,177],"framework":[121],"that":[122],"not":[123],"only":[124],"discerns":[125],"relationships":[128],"within":[129],"generative":[131],"process":[132],"but":[133],"also":[134],"isolates":[135],"critical":[136],"variables":[138],"from":[139],"typically":[141],"dense":[142],"representations.":[146],"We":[147,186],"provide":[148],"theoretical":[149],"evidence":[150],"identifiability":[153],"these":[155],"variables.":[156],"Then,":[157],"use":[160],"identified":[163],"relationship,":[165],"construct":[167],"causal-indispensable":[168],"representations,":[170],"enabling":[171],"training":[173],"policies":[175],"over":[176],"more":[178],"advantageous":[179],"subset":[180],"agent's":[183],"space.":[185],"demonstrate":[187],"efficacy":[189],"our":[191,197],"through":[193],"extensive":[194],"experiments,":[195],"showcasing":[196],"outperforms":[199],"state-of-the-art":[200],"methods.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2025-10-10T00:00:00"}