{"id":"https://openalex.org/W3081226161","doi":"https://doi.org/10.1145/3394486.3403175","title":"Joint Policy-Value Learning for Recommendation","display_name":"Joint Policy-Value Learning for Recommendation","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3081226161","doi":"https://doi.org/10.1145/3394486.3403175","mag":"3081226161"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403175","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5083237271","display_name":"Olivier Jeunen","orcid":"https://orcid.org/0000-0001-6256-5814"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Olivier Jeunen","raw_affiliation_strings":["University of Antwerp, Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024601290","display_name":"David Rohde","orcid":"https://orcid.org/0000-0002-0661-6266"},"institutions":[{"id":"https://openalex.org/I4210161401","display_name":"Criteo (France)","ror":"https://ror.org/04vyg0r47","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210161401"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"David Rohde","raw_affiliation_strings":["Criteo AI Lab, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Criteo AI Lab, Paris, France","institution_ids":["https://openalex.org/I4210161401"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003359035","display_name":"Flavian Vasile","orcid":"https://orcid.org/0009-0006-3578-5655"},"institutions":[{"id":"https://openalex.org/I4210161401","display_name":"Criteo (France)","ror":"https://ror.org/04vyg0r47","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210161401"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Flavian Vasile","raw_affiliation_strings":["Criteo AI Lab, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Criteo AI Lab, Paris, France","institution_ids":["https://openalex.org/I4210161401"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073218160","display_name":"Martin Bompaire","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161401","display_name":"Criteo (France)","ror":"https://ror.org/04vyg0r47","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210161401"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Martin Bompaire","raw_affiliation_strings":["Criteo AI Lab, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Criteo AI Lab, Paris, France","institution_ids":["https://openalex.org/I4210161401"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4168,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.89553304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1223","last_page":"1233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9968000054359436,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9919999837875366,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.8559545278549194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8064967393875122},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7338055372238159},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6821410655975342},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5677046775817871},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5277538895606995},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.5187540054321289},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5006687641143799},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.457607239484787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41830259561538696},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32505589723587036},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07869967818260193}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8559545278549194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8064967393875122},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7338055372238159},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6821410655975342},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5677046775817871},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5277538895606995},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5187540054321289},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5006687641143799},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.457607239484787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41830259561538696},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32505589723587036},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07869967818260193},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"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/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394486.3403175","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:c:irua:174142","is_oa":false,"landing_page_url":"https://hdl.handle.net/10067/1741420151162165141","pdf_url":null,"source":{"id":"https://openalex.org/S4306401849","display_name":"Institutional Repository University of Antwerp (University of Antwerp)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149213910","host_organization_name":"University of Antwerp","host_organization_lineage":["https://openalex.org/I149213910"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1809653203","https://openalex.org/W1973948212","https://openalex.org/W2034368206","https://openalex.org/W2045745608","https://openalex.org/W2054141820","https://openalex.org/W2074694452","https://openalex.org/W2085040216","https://openalex.org/W2102017903","https://openalex.org/W2108738385","https://openalex.org/W2112420033","https://openalex.org/W2119717200","https://openalex.org/W2122124659","https://openalex.org/W2151568819","https://openalex.org/W2155027007","https://openalex.org/W2157711174","https://openalex.org/W2159309155","https://openalex.org/W2163162311","https://openalex.org/W2188353343","https://openalex.org/W2488917374","https://openalex.org/W2498119267","https://openalex.org/W2511414107","https://openalex.org/W2558073743","https://openalex.org/W2785875001","https://openalex.org/W2902572901","https://openalex.org/W2908670005","https://openalex.org/W2911802745","https://openalex.org/W2912745432","https://openalex.org/W2944441143","https://openalex.org/W2944832664","https://openalex.org/W2946400218","https://openalex.org/W2952012669","https://openalex.org/W2962785510","https://openalex.org/W2962818688","https://openalex.org/W2963085847","https://openalex.org/W2963489350","https://openalex.org/W2966283211","https://openalex.org/W2970971581","https://openalex.org/W2972520532","https://openalex.org/W2993053728","https://openalex.org/W3003609932","https://openalex.org/W3009804075","https://openalex.org/W3098638686","https://openalex.org/W3099420497","https://openalex.org/W3099464630","https://openalex.org/W3104881842","https://openalex.org/W3105114834","https://openalex.org/W4288280739","https://openalex.org/W4295312788"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2066431708","https://openalex.org/W4384133558","https://openalex.org/W3025615835","https://openalex.org/W173210993","https://openalex.org/W2390660599","https://openalex.org/W3028847759","https://openalex.org/W3163462160","https://openalex.org/W4210625552"],"abstract_inverted_index":{"Conventional":[0],"approaches":[1],"to":[2,71,86,101],"recommendation":[3,66],"often":[4],"do":[5,26],"not":[6,27,36,44],"explicitly":[7],"take":[8],"into":[9],"account":[10],"information":[11],"on":[12],"previously":[13],"shown":[14],"recommendations":[15],"and":[16,77],"their":[17,62],"recorded":[18],"responses.":[19],"One":[20],"reason":[21],"is":[22,43,90],"that,":[23],"since":[24],"we":[25],"know":[28],"the":[29,33,65,72,78],"outcome":[30],"of":[31,74,80,82],"actions":[32],"system":[34],"did":[35],"take,":[37],"learning":[38,54],"directly":[39],"from":[40],"such":[41],"logs":[42],"a":[45,91,98],"straightforward":[46],"task.":[47,93],"Several":[48],"methods":[49],"for":[50,64],"off-policy":[51],"or":[52],"counterfactual":[53],"have":[55],"been":[56],"proposed":[57],"in":[58],"recent":[59],"years,":[60],"but":[61],"efficacy":[63],"task":[67],"remains":[68],"understudied.":[69],"Due":[70],"limitations":[73],"offline":[75],"datasets":[76],"lack":[79],"access":[81],"most":[83],"academic":[84],"researchers":[85],"online":[87],"experiments,":[88],"this":[89,102],"non-trivial":[92],"Simulation":[94],"environments":[95],"can":[96],"provide":[97],"reproducible":[99],"solution":[100],"problem.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}