{"id":"https://openalex.org/W4290875274","doi":"https://doi.org/10.1145/3534678.3539341","title":"MDP2 Forest: A Constrained Continuous Multi-dimensional Policy Optimization Approach for Short-video Recommendation","display_name":"MDP2 Forest: A Constrained Continuous Multi-dimensional Policy Optimization Approach for Short-video Recommendation","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290875274","doi":"https://doi.org/10.1145/3534678.3539341"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539341","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539341","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3534678.3539341","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109583388","display_name":"Sizhe Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sizhe Yu","raw_affiliation_strings":["Shanghai University of Finance and Economics, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383203","display_name":"Ziyi Liu","orcid":"https://orcid.org/0000-0002-2407-9599"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Liu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076397911","display_name":"Shixiang Wan","orcid":"https://orcid.org/0000-0001-8644-9893"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixiang Wan","raw_affiliation_strings":["Tencent Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent Inc., Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100661833","display_name":"Jia Zheng","orcid":"https://orcid.org/0009-0004-0893-9327"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Zheng","raw_affiliation_strings":["Tencent Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent Inc., Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081888630","display_name":"Li Zang","orcid":"https://orcid.org/0000-0002-3183-8899"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zang Li","raw_affiliation_strings":["Tencent Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent Inc., Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403433","display_name":"Fan Zhou","orcid":"https://orcid.org/0000-0002-0900-6965"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhou","raw_affiliation_strings":["Shanghai University of Finance and Economics, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5109583388"],"corresponding_institution_ids":["https://openalex.org/I181679659"],"apc_list":null,"apc_paid":null,"fwci":1.0296,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73701125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2388","last_page":"2398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.996399998664856,"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":0.996399998664856,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9879000186920166,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7425863742828369},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.7339949607849121},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6187453269958496},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.5175015926361084},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.502274751663208},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5022101402282715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4964504837989807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4868308901786804},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.455973744392395},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45469772815704346},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4304431080818176},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36197400093078613},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.21865633130073547},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15041086077690125},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12987864017486572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7425863742828369},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7339949607849121},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6187453269958496},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.5175015926361084},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.502274751663208},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5022101402282715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4964504837989807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4868308901786804},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.455973744392395},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45469772815704346},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4304431080818176},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36197400093078613},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.21865633130073547},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15041086077690125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12987864017486572},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539341","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539341","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3534678.3539341","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539341","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2018472295","https://openalex.org/W2164985671","https://openalex.org/W2208550830","https://openalex.org/W2305754340","https://openalex.org/W2496119153","https://openalex.org/W2787023317","https://openalex.org/W2890118063","https://openalex.org/W2905278593","https://openalex.org/W2911373802","https://openalex.org/W2913023375","https://openalex.org/W2937302337","https://openalex.org/W2945684222","https://openalex.org/W2981569692","https://openalex.org/W2982108874","https://openalex.org/W2997876178","https://openalex.org/W3034203759","https://openalex.org/W3035302362","https://openalex.org/W3092103025","https://openalex.org/W3093242741","https://openalex.org/W3103988283","https://openalex.org/W3140315313","https://openalex.org/W3153906321","https://openalex.org/W3156939347","https://openalex.org/W3164238513","https://openalex.org/W3166751026","https://openalex.org/W3176728897","https://openalex.org/W3194327889","https://openalex.org/W3209710210","https://openalex.org/W3210910782","https://openalex.org/W4311645551","https://openalex.org/W6773134140"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W3123835761","https://openalex.org/W1657011257"],"abstract_inverted_index":{"In":[0,65],"the":[1,7,38,47,70,115,131,148,153,157,180],"ecology":[2],"of":[3,11,90,107,117,133,147,169,177],"short":[4],"video":[5,13],"platforms,":[6],"optimal":[8],"exposure":[9,58,71],"proportion":[10,72],"each":[12,43],"category":[14],"is":[15],"crucial":[16],"to":[17,36,137,165],"guide":[18],"recommendation":[19,32],"systems":[20,33],"and":[21,57,127,152],"content":[22],"production":[23],"in":[24,62,145],"a":[25,75,86,94,166],"macroscopic":[26],"way.":[27],"Though":[28],"extensive":[29],"studies":[30],"on":[31,101,124,179],"are":[34],"devoted":[35],"providing":[37],"most":[39],"well-matched":[40],"videos":[41],"for":[42],"view":[44],"request,":[45],"fitting":[46],"data":[48],"without":[49],"considering":[50],"inherent":[51],"biases":[52],"such":[53,172],"as":[54,74,173],"selection":[55],"bias":[56,59],"will":[60],"result":[61],"serious":[63],"issues.":[64],"this":[66],"paper,":[67],"we":[68],"formalize":[69],"strategy":[73],"policy-making":[76],"problem":[77],"with":[78],"multi-dimensional":[79,181],"continuous":[80],"treatment":[81,149],"under":[82],"certain":[83],"constraints":[84,178],"from":[85],"causal":[87,102,142],"inference":[88,143],"point":[89],"view.":[91],"We":[92],"propose":[93],"novel":[95],"ensemble":[96],"policy":[97,119,139],"learning":[98,120,140],"method":[99,161],"based":[100],"trees,":[103],"called":[104],"Maximum":[105],"Difference":[106],"Preference":[108],"Point":[109],"Forest":[110,160],"(MDP2":[111],"Forest),":[112],"which":[113],"overcomes":[114],"shortcomings":[116],"existing":[118],"approaches.":[121],"Experimental":[122],"results":[123],"both":[125],"simulated":[126],"synthetic":[128],"datasets":[129],"show":[130],"superiority":[132],"our":[134],"algorithm":[135],"compared":[136],"other":[138],"or":[141],"methods":[144],"terms":[146],"estimation":[150],"accuracy":[151],"mean":[154],"regret.":[155],"Furthermore,":[156],"proposed":[158],"MDP2":[159],"can":[162],"also":[163],"adapt":[164],"wide":[167],"range":[168],"business":[170],"settings":[171],"imposing":[174],"different":[175],"kinds":[176],"treatment.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}