{"id":"https://openalex.org/W4367319168","doi":"https://doi.org/10.1145/3543873.3587661","title":"Investigating Action-Space Generalization in Reinforcement Learning for Recommendation Systems","display_name":"Investigating Action-Space Generalization in Reinforcement Learning for Recommendation Systems","publication_year":2023,"publication_date":"2023-04-28","ids":{"openalex":"https://openalex.org/W4367319168","doi":"https://doi.org/10.1145/3543873.3587661"},"language":"en","primary_location":{"id":"doi:10.1145/3543873.3587661","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543873.3587661","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543873.3587661","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","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/10.1145/3543873.3587661","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018976973","display_name":"Abhishek Naik","orcid":"https://orcid.org/0009-0008-1427-1609"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Abhishek Naik","raw_affiliation_strings":["University of Alberta, Canada and Alberta Machine Intelligence Institute (Amii), Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Canada and Alberta Machine Intelligence Institute (Amii), Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033769984","display_name":"Bo Chang","orcid":"https://orcid.org/0000-0001-7429-7212"},"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":"Bo Chang","raw_affiliation_strings":["Google Research, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082408006","display_name":"Alexandros Karatzoglou","orcid":"https://orcid.org/0000-0001-6063-9023"},"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":"Alexandros Karatzoglou","raw_affiliation_strings":["Google Research, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045775773","display_name":"Martin Mladenov","orcid":"https://orcid.org/0009-0007-5565-5126"},"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":"Martin Mladenov","raw_affiliation_strings":["Google Research, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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 H. Chi","raw_affiliation_strings":["Google Research, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","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":false,"raw_author_name":"Minmin Chen","raw_affiliation_strings":["Google Research, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5018976973"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03763624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"966","last_page":"972"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9923999905586243,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.977400004863739,"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/generalization","display_name":"Generalization","score":0.7150523662567139},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7068372964859009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995920538902283},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6543412208557129},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5888586044311523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5178421139717102},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37947967648506165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14770346879959106}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7150523662567139},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7068372964859009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995920538902283},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6543412208557129},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5888586044311523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5178421139717102},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37947967648506165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14770346879959106},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":1,"locations":[{"id":"doi:10.1145/3543873.3587661","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543873.3587661","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543873.3587661","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3543873.3587661","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543873.3587661","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543873.3587661","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367319168.pdf","grobid_xml":"https://content.openalex.org/works/W4367319168.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2086504823","https://openalex.org/W2131600418","https://openalex.org/W2145339207","https://openalex.org/W2152808281","https://openalex.org/W2153110279","https://openalex.org/W2164858444","https://openalex.org/W2323594155","https://openalex.org/W2902572901","https://openalex.org/W2902907165","https://openalex.org/W2964179661","https://openalex.org/W3041202696","https://openalex.org/W3116249021","https://openalex.org/W4230563027"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W3162204513","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548"],"abstract_inverted_index":{"Recommender":[0],"systems":[1,15],"are":[2],"used":[3,109],"to":[4,7,32,62,115],"suggest":[5,101],"items":[6,53],"users":[8],"based":[9],"on":[10,98,110,126],"the":[11,80,85,103,116,122,137,144],"users\u2019":[12],"preferences.":[13],"Such":[14],"often":[16],"deal":[17],"with":[18],"massive":[19],"item":[20],"sets":[21],"and":[22,47,59,140],"incredibly":[23],"sparse":[24,75],"user-item":[25],"interactions,":[26],"which":[27],"makes":[28],"it":[29],"very":[30],"challenging":[31],"generate":[33],"high-quality":[34],"personalized":[35],"recommendations.":[36],"Reinforcement":[37],"learning":[38],"(RL)":[39],"is":[40,106],"a":[41,91,132],"framework":[42],"for":[43,147],"sequential":[44],"decision":[45],"making":[46],"naturally":[48],"formulates":[49],"recommender-system":[50],"tasks:":[51],"recommending":[52],"as":[54,90],"actions":[55],"in":[56],"different":[57],"user":[58,65],"context":[60],"states":[61],"maximize":[63],"long-term":[64],"experience.":[66],"We":[67],"investigate":[68],"two":[69],"RL":[70],"policy":[71,86],"parameterizations":[72],"that":[73,102],"generalize":[74],"user-items":[76],"interactions":[77],"by":[78],"leveraging":[79],"relationships":[81],"between":[82],"actions:":[83],"parameterizing":[84],"over":[87],"action":[88,119],"features":[89,120],"softmax":[92,123],"or":[93],"Gaussian":[94,104,145],"distribution.":[95],"Our":[96],"experiments":[97],"synthetic":[99],"problems":[100],"parameterization\u2014which":[105],"not":[107],"commonly":[108],"recommendation":[111],"tasks\u2014is":[112],"more":[113,133],"robust":[114],"set":[117],"of":[118,136,143],"than":[121],"parameterization.":[124],"Based":[125],"these":[127],"promising":[128],"results,":[129],"we":[130],"propose":[131],"thorough":[134],"investigation":[135],"theoretical":[138],"properties":[139],"empirical":[141],"benefits":[142],"parameterization":[146],"recommender":[148],"systems.":[149]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}