{"id":"https://openalex.org/W4319792126","doi":"https://doi.org/10.1145/3543507.3583244","title":"Exploration and Regularization of the Latent Action Space in Recommendation","display_name":"Exploration and Regularization of the Latent Action Space in Recommendation","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4319792126","doi":"https://doi.org/10.1145/3543507.3583244"},"language":"en","primary_location":{"id":"doi:10.1145/3543507.3583244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543507.3583244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.03431","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100600807","display_name":"Shuchang Liu","orcid":"https://orcid.org/0000-0002-1440-911X"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuchang Liu","raw_affiliation_strings":["Kuaishou Technology, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016589992","display_name":"Qingpeng Cai","orcid":"https://orcid.org/0000-0001-6451-9299"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingpeng Cai","raw_affiliation_strings":["Kuaishou Technology, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101919618","display_name":"Bowen Sun","orcid":"https://orcid.org/0000-0003-3625-0477"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Sun","raw_affiliation_strings":["Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043861652","display_name":"Yuhao Wang","orcid":"https://orcid.org/0000-0002-6051-8659"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuhao Wang","raw_affiliation_strings":["City University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005205575","display_name":"Ji Tong Jiang","orcid":"https://orcid.org/0000-0002-9632-8400"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Jiang","raw_affiliation_strings":["Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086177569","display_name":"Dong Zheng","orcid":"https://orcid.org/0000-0003-0424-9658"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Zheng","raw_affiliation_strings":["Kuaishou Technology, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001339397","display_name":"Peng Jiang","orcid":"https://orcid.org/0000-0002-9266-0780"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Jiang","raw_affiliation_strings":["Kuaishou Technology, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062939922","display_name":"Kun Gai","orcid":"https://orcid.org/0000-0002-3636-3618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Gai","raw_affiliation_strings":["Unaffiliated, China"],"affiliations":[{"raw_affiliation_string":"Unaffiliated, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645854","display_name":"Xiangyu Zhao","orcid":"https://orcid.org/0000-0003-2926-4416"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhao","raw_affiliation_strings":["City University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100329828","display_name":"Yongfeng Zhang","orcid":"https://orcid.org/0000-0003-2633-8555"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongfeng Zhang","raw_affiliation_strings":["Rutgers University, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100600807"],"corresponding_institution_ids":["https://openalex.org/I4401726859"],"apc_list":null,"apc_paid":null,"fwci":15.4871,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.98993054,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"833","last_page":"844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9983000159263611,"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":0.9916999936103821,"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":0.7834210395812988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7831889390945435},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7388343811035156},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6894175410270691},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6795001029968262},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.583836555480957},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5503621697425842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5494904518127441},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5219290256500244},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4658423662185669},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4559803605079651},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4458523392677307},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12406370043754578}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7834210395812988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831889390945435},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7388343811035156},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6894175410270691},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6795001029968262},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.583836555480957},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5503621697425842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5494904518127441},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5219290256500244},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4658423662185669},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4559803605079651},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4458523392677307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12406370043754578},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3543507.3583244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543507.3583244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2302.03431","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.03431","pdf_url":"https://arxiv.org/pdf/2302.03431","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.03431","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.03431","pdf_url":"https://arxiv.org/pdf/2302.03431","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.550000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G553902691","display_name":null,"funder_award_id":"Start-up","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"},{"id":"https://openalex.org/G7271486925","display_name":null,"funder_award_id":"9360163","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"},{"id":"https://openalex.org/G8226490486","display_name":null,"funder_award_id":"9360163","funder_id":"https://openalex.org/F4320334123","funder_display_name":"Hong Kong Institute for Data Science"}],"funders":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"},{"id":"https://openalex.org/F4320319065","display_name":"Aromatic Plant Research Center","ror":"https://ror.org/05eebgw43"},{"id":"https://openalex.org/F4320334123","display_name":"Hong Kong Institute for Data Science","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319792126.pdf","grobid_xml":"https://content.openalex.org/works/W4319792126.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2054141820","https://openalex.org/W2135263912","https://openalex.org/W2137063737","https://openalex.org/W2149427297","https://openalex.org/W2171279286","https://openalex.org/W2475334473","https://openalex.org/W2617539464","https://openalex.org/W2746011824","https://openalex.org/W2783272285","https://openalex.org/W2783944588","https://openalex.org/W2787938642","https://openalex.org/W2788295351","https://openalex.org/W2799544270","https://openalex.org/W2899457523","https://openalex.org/W2902572901","https://openalex.org/W2937556626","https://openalex.org/W2945488061","https://openalex.org/W2948345531","https://openalex.org/W2950275995","https://openalex.org/W2953132212","https://openalex.org/W2963085847","https://openalex.org/W2963367478","https://openalex.org/W2963619374","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2972801466","https://openalex.org/W2984100107","https://openalex.org/W2984869362","https://openalex.org/W3003416843","https://openalex.org/W3024683329","https://openalex.org/W3034853385","https://openalex.org/W3040094401","https://openalex.org/W3049342604","https://openalex.org/W3093531652","https://openalex.org/W3099726771","https://openalex.org/W3101707147","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3104966867","https://openalex.org/W3116249021","https://openalex.org/W3116873649","https://openalex.org/W3123348991","https://openalex.org/W3134624922","https://openalex.org/W3153088333","https://openalex.org/W3153252032","https://openalex.org/W3157410348","https://openalex.org/W3172360140","https://openalex.org/W3178835722","https://openalex.org/W3185693672","https://openalex.org/W3205450119","https://openalex.org/W3208231292","https://openalex.org/W3211540990","https://openalex.org/W4212951676","https://openalex.org/W4225156780","https://openalex.org/W4226210383","https://openalex.org/W4281621664","https://openalex.org/W4288110508","https://openalex.org/W4288614963","https://openalex.org/W4292419518","https://openalex.org/W4296591867","https://openalex.org/W4300415226","https://openalex.org/W4321480051","https://openalex.org/W4394672593"],"related_works":["https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2037601570","https://openalex.org/W2912947802","https://openalex.org/W2123856982"],"abstract_inverted_index":{"In":[0,100],"recommender":[1],"systems,":[2],"reinforcement":[3],"learning":[4,54,136],"solutions":[5],"have":[6],"effectively":[7],"boosted":[8],"recommendation":[9,26,154],"performance":[10],"because":[11],"of":[12,24,31],"their":[13],"ability":[14],"to":[15,102,124,133,156],"capture":[16],"long-term":[17],"user-system":[18],"interaction.":[19],"However,":[20],"the":[21,25,57,60,79,89,93,98,104,107,135],"action":[22,109],"space":[23,82],"policy":[27,58],"is":[28,151],"a":[29,39,50,66,84,118,130],"list":[30,62,95],"items,":[32],"which":[33],"could":[34],"be":[35],"extremely":[36],"large":[37],"with":[38,117],"dynamic":[40],"candidate":[41],"item":[42,61,94],"pool.":[43],"To":[44],"overcome":[45],"this":[46],"challenge,":[47],"we":[48,111],"propose":[49],"hyper-actor":[51],"and":[52,70,88,128,145],"critic":[53],"framework":[55,150],"where":[56],"decomposes":[59],"generation":[63],"process":[64],"into":[65,83],"hyper-action":[67,86],"inference":[68,126],"step":[69,77,91],"an":[71,113],"effect-action":[72],"selection":[73],"step.":[74],"The":[75],"first":[76],"maps":[78],"given":[80],"state":[81],"vectorized":[85],"space,":[87],"second":[90],"selects":[92],"based":[96],"on":[97,142],"hyper-action.":[99],"order":[101],"regulate":[103],"discrepancy":[105],"between":[106],"two":[108],"spaces,":[110],"design":[112],"alignment":[114],"module":[115,132],"along":[116],"kernel":[119],"mapping":[120],"function":[121],"for":[122],"items":[123],"ensure":[125],"accuracy":[127],"include":[129],"supervision":[131],"stabilize":[134],"process.":[137],"We":[138],"build":[139],"simulated":[140],"environments":[141],"public":[143],"datasets":[144],"empirically":[146],"show":[147],"that":[148],"our":[149],"superior":[152],"in":[153],"compared":[155],"standard":[157],"RL":[158],"baselines.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}