{"id":"https://openalex.org/W4296604485","doi":"https://doi.org/10.1145/3523227.3546758","title":"Off-Policy Actor-critic for Recommender Systems","display_name":"Off-Policy Actor-critic for Recommender Systems","publication_year":2022,"publication_date":"2022-09-13","ids":{"openalex":"https://openalex.org/W4296604485","doi":"https://doi.org/10.1145/3523227.3546758"},"language":"en","primary_location":{"id":"doi:10.1145/3523227.3546758","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3523227.3546758","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3523227.3546758","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3523227.3546758","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100699702","display_name":"Minmin Chen","orcid":"https://orcid.org/0000-0002-7342-9022"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minmin Chen","raw_affiliation_strings":["Google, United States"],"affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101493343","display_name":"Can Xu","orcid":"https://orcid.org/0000-0002-4254-8678"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Can Xu","raw_affiliation_strings":["Google, United States"],"affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036924199","display_name":"Vince Gatto","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vince Gatto","raw_affiliation_strings":["Google, United States"],"affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112547858","display_name":"Devanshu Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devanshu Jain","raw_affiliation_strings":["Google, United States"],"affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102493293","display_name":"Aviral Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aviral Kumar","raw_affiliation_strings":["Google, United States"],"affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028125399","display_name":"Ed H.","orcid":"https://orcid.org/0000-0003-3230-5338"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ed Chi","raw_affiliation_strings":["Google, United States"],"affiliations":[{"raw_affiliation_string":"Google, United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100699702"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":4.7465,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.95630856,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"338","last_page":"349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9993000030517578,"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":0.9993000030517578,"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/T10603","display_name":"Smart Grid Energy Management","score":0.998199999332428,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9959999918937683,"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/recommender-system","display_name":"Recommender system","score":0.8796707391738892},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8748626112937927},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.854944109916687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7940414547920227},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5696008801460266},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.5130900144577026},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.4557494819164276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3688383102416992},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33600014448165894}],"concepts":[{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8796707391738892},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8748626112937927},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.854944109916687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940414547920227},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5696008801460266},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.5130900144577026},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.4557494819164276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3688383102416992},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33600014448165894},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","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/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3523227.3546758","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3523227.3546758","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3523227.3546758","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3523227.3546758","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3523227.3546758","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3523227.3546758","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296604485.pdf","grobid_xml":"https://content.openalex.org/works/W4296604485.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2042281163","https://openalex.org/W2054141820","https://openalex.org/W2060846151","https://openalex.org/W2077611535","https://openalex.org/W2120346334","https://openalex.org/W2160308170","https://openalex.org/W2186820913","https://openalex.org/W2512971201","https://openalex.org/W2746553466","https://openalex.org/W2784068709","https://openalex.org/W2787933113","https://openalex.org/W2902572901","https://openalex.org/W2951625652","https://openalex.org/W2962736495","https://openalex.org/W2963842088","https://openalex.org/W2964108915","https://openalex.org/W2965512832","https://openalex.org/W3001218531","https://openalex.org/W3003416843","https://openalex.org/W3033324992","https://openalex.org/W3034853385","https://openalex.org/W3080077280","https://openalex.org/W3081226161","https://openalex.org/W3099117208","https://openalex.org/W3099420497","https://openalex.org/W3116249021","https://openalex.org/W3118210634","https://openalex.org/W3123956618","https://openalex.org/W3173984942","https://openalex.org/W3198076800","https://openalex.org/W3201286590","https://openalex.org/W4212961739","https://openalex.org/W4213113302","https://openalex.org/W4283789472","https://openalex.org/W4288083766","https://openalex.org/W4293585414","https://openalex.org/W4361023176","https://openalex.org/W6630221451","https://openalex.org/W6677737365"],"related_works":["https://openalex.org/W2968745142","https://openalex.org/W2809363009","https://openalex.org/W2369936857","https://openalex.org/W2348159088","https://openalex.org/W2045871438","https://openalex.org/W2499363748","https://openalex.org/W2350747448","https://openalex.org/W2368095327","https://openalex.org/W4296604485","https://openalex.org/W4319083788"],"abstract_inverted_index":{"Industrial":[0],"recommendation":[1],"platforms":[2],"are":[3],"increasingly":[4],"concerned":[5],"with":[6],"how":[7],"to":[8,14,49,57,104],"make":[9],"recommendations":[10],"that":[11],"cause":[12],"users":[13,64],"enjoy":[15],"their":[16],"long":[17,51],"term":[18,52],"experience":[19],"on":[20,94],"the":[21,95,105],"platform.":[22],"Reinforcement":[23],"learning":[24,102],"emerged":[25],"naturally":[26],"as":[27],"an":[28],"appealing":[29],"approach":[30],"for":[31],"its":[32,78],"promise":[33],"in":[34,81,101],"1)":[35],"combating":[36],"feedback":[37],"loop":[38],"effect":[39],"resulted":[40],"from":[41],"myopic":[42],"system":[43],"behaviors;":[44],"and":[45,65,72,90],"2)":[46],"sequential":[47],"planning":[48],"optimize":[50],"outcome.":[53],"Scaling":[54],"RL":[55,76,84],"algorithms":[56],"production":[58],"recommender":[59],"systems":[60],"serving":[61],"billions":[62],"of":[63,74,87],"contents,":[66],"however":[67],"remain":[68],"challenging.":[69],"Sample":[70],"inefficiency":[71],"instability":[73],"online":[75],"hinder":[77],"widespread":[79],"adoption":[80],"production.":[82],"Offline":[83],"enables":[85],"usage":[86],"off-policy":[88],"data":[89],"batch":[91],"learning.":[92],"It":[93],"other":[96],"hand":[97],"faces":[98],"significant":[99],"challenges":[100],"due":[103],"distribution":[106],"shift.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}