{"id":"https://openalex.org/W4367047389","doi":"https://doi.org/10.1145/3543507.3583259","title":"Two-Stage Constrained Actor-Critic for Short Video Recommendation","display_name":"Two-Stage Constrained Actor-Critic for Short Video Recommendation","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4367047389","doi":"https://doi.org/10.1145/3543507.3583259"},"language":"en","primary_location":{"id":"doi:10.1145/3543507.3583259","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543507.3583259","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":["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/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":true,"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/A5054607440","display_name":"Zhenghai Xue","orcid":"https://orcid.org/0000-0002-9340-0366"},"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":"Zhenghai Xue","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/A5089300674","display_name":"Chi Zhang","orcid":null},"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":"Chi Zhang","raw_affiliation_strings":["Kuaishou Technology, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wanqi Xue","orcid":"https://orcid.org/0000-0003-3490-1088"},"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":"Wanqi Xue","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/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":false,"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/A5053491985","display_name":"Ruohan Zhan","orcid":"https://orcid.org/0000-0002-3426-2784"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ruohan Zhan","raw_affiliation_strings":["Hong Kong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018244850","display_name":"Xueliang Wang","orcid":null},"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":"Xueliang Wang","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/A5026138710","display_name":"Tianyou Zuo","orcid":"https://orcid.org/0000-0002-2733-1235"},"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":"Tianyou Zuo","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/A5016249842","display_name":"Wentao Xie","orcid":"https://orcid.org/0000-0002-6733-2291"},"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":"Wentao Xie","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/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":"last","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":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5016589992"],"corresponding_institution_ids":["https://openalex.org/I4401726859"],"apc_list":null,"apc_paid":null,"fwci":6.5675,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.97409917,"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":"865","last_page":"875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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":0.9955999851226807,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9926000237464905,"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":0.9876999855041504,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8556178212165833},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7671465277671814},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7468863129615784},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.6610697507858276},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6042901277542114},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5878673195838928},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5488553047180176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4417334496974945},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4299907386302948},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.41363489627838135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8556178212165833},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7671465277671814},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7468863129615784},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.6610697507858276},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6042901277542114},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5878673195838928},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5488553047180176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4417334496974945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4299907386302948},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41363489627838135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3543507.3583259","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543507.3583259","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:repository.hkust.edu.hk:1783.1-127349","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-127349","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1514587017","https://openalex.org/W2469508028","https://openalex.org/W2475334473","https://openalex.org/W2535327675","https://openalex.org/W2788295351","https://openalex.org/W2790759781","https://openalex.org/W2809162153","https://openalex.org/W2902572901","https://openalex.org/W2950275995","https://openalex.org/W2955026632","https://openalex.org/W2963619374","https://openalex.org/W2963842088","https://openalex.org/W2972510393","https://openalex.org/W3003931103","https://openalex.org/W3012881846","https://openalex.org/W3093519337","https://openalex.org/W3102778384","https://openalex.org/W3116873649","https://openalex.org/W3154925836","https://openalex.org/W3162902207","https://openalex.org/W3189576409","https://openalex.org/W3211540990","https://openalex.org/W4214717370","https://openalex.org/W4287756699","https://openalex.org/W4290927958","https://openalex.org/W4290943562","https://openalex.org/W4290943719","https://openalex.org/W4290944246","https://openalex.org/W4292419518","https://openalex.org/W4306317504"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W2922107804"],"abstract_inverted_index":{"The":[0],"wide":[1],"popularity":[2],"of":[3,39,83,87,106,181,196,218,224,236],"short":[4,107,225],"videos":[5],"on":[6,18,185,255],"social":[7],"media":[8],"poses":[9],"new":[10],"opportunities":[11],"and":[12,28,31,36,165,239],"challenges":[13],"to":[14,79,126,147,159,169,251],"optimize":[15,148,161,252],"recommender":[16],"systems":[17],"the":[19,26,45,48,53,60,72,75,81,85,104,162,173,179,186,194,204,211,216,248,256],"video-sharing":[20],"platforms.":[21],"Users":[22],"sequentially":[23],"interact":[24],"with":[25,41],"system":[27,250],"provide":[29],"complex":[30],"multi-faceted":[32],"responses,":[33],"including":[34],"WatchTime":[35,56,238],"various":[37],"types":[38],"interactions":[40,90],"multiple":[42,88],"videos.":[43],"On":[44,71],"one":[46],"hand,":[47,74],"platforms":[49,76],"aim":[50],"at":[51],"optimizing":[52,203],"users\u2019":[54],"cumulative":[55],"(main":[57],"goal)":[58],"in":[59,129,172,201,221,234,247],"long":[61],"term,":[62],"which":[63,176],"can":[64],"be":[65],"effectively":[66,177],"optimized":[67],"by":[68],"Reinforcement":[69],"Learning.":[70],"other":[73,232],"also":[77],"need":[78],"satisfy":[80],"constraint":[82],"accommodating":[84],"responses":[86],"user":[89,253],"(auxiliary":[91],"goals)":[92],"such":[93],"as":[94,110,207,209],"Like,":[95],"Follow,":[96],"Share,":[97],"etc.":[98],"In":[99,152],"this":[100,130,182],"paper,":[101],"we":[102,143,155,192],"formulate":[103],"problem":[105],"video":[108,226],"recommendation":[109],"a":[111,134,157],"Constrained":[112],"Markov":[113],"Decision":[114],"Process":[115],"(CMDP).":[116],"We":[117,132,213],"find":[118],"that":[119],"traditional":[120],"constrained":[121,137],"reinforcement":[122],"learning":[123],"algorithms":[124],"fail":[125],"work":[127],"well":[128,208],"setting.":[131],"propose":[133],"novel":[135],"two-stage":[136],"actor-critic":[138],"method:":[139],"At":[140],"stage":[141,153],"one,":[142],"learn":[144,156],"individual":[145],"policies":[146,170],"each":[149],"auxiliary":[150],"signal.":[151],"two,":[154],"policy":[158,184],"(i)":[160],"main":[163,183,205],"signal":[164],"(ii)":[166],"stay":[167],"close":[168],"learned":[171],"first":[174],"stage,":[175],"guarantees":[178],"performance":[180],"auxiliaries.":[187],"Through":[188],"extensive":[189],"offline":[190],"evaluations,":[191],"demonstrate":[193],"effectiveness":[195],"our":[197,219],"method":[198,220],"over":[199],"alternatives":[200],"both":[202,237],"goal":[206],"balancing":[210],"others.":[212],"further":[214],"show":[215],"advantage":[217],"live":[222],"experiments":[223],"recommendations,":[227],"where":[228],"it":[229],"significantly":[230],"outperforms":[231],"baselines":[233],"terms":[235],"interactions.":[240],"Our":[241],"approach":[242],"has":[243],"been":[244],"fully":[245],"launched":[246],"production":[249],"experiences":[254],"platform.":[257]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}