{"id":"https://openalex.org/W2981211936","doi":"https://doi.org/10.1145/3359554","title":"Interactive Recommendation with User-Specific Deep Reinforcement Learning","display_name":"Interactive Recommendation with User-Specific Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981211936","doi":"https://doi.org/10.1145/3359554","mag":"2981211936"},"language":"en","primary_location":{"id":"doi:10.1145/3359554","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3359554","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-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/A5100736933","display_name":"Yu Lei","orcid":"https://orcid.org/0000-0001-8482-3140"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yu Lei","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-8482-3140","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100408983","display_name":"Wenjie Li","orcid":"https://orcid.org/0000-0002-7360-8864"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenjie Li","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.7587,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.97390009,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"13","issue":"6","first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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":0.9889000058174133,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8320114016532898},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8095442056655884},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7338951826095581},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6842050552368164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5772207379341125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5691332221031189},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5245299935340881},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4755808115005493},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.47275787591934204},{"id":"https://openalex.org/keywords/user-modeling","display_name":"User modeling","score":0.4596182703971863},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4515090584754944},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44796067476272583},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.13912546634674072},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07265588641166687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8320114016532898},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8095442056655884},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7338951826095581},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6842050552368164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5772207379341125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5691332221031189},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5245299935340881},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4755808115005493},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.47275787591934204},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.4596182703971863},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4515090584754944},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44796067476272583},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.13912546634674072},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07265588641166687},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3359554","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3359554","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1372504386","display_name":"\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684\u65b0\u578b\u751f\u6210\u5f0f\u6458\u8981\u6a21\u578b\u7814\u7a76","funder_award_id":"61672445","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4287765434","display_name":null,"funder_award_id":"G-YBP6","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1486317198","https://openalex.org/W1595483645","https://openalex.org/W1980158807","https://openalex.org/W1994389483","https://openalex.org/W2029604041","https://openalex.org/W2054141820","https://openalex.org/W2058879737","https://openalex.org/W2071133755","https://openalex.org/W2089083003","https://openalex.org/W2091780923","https://openalex.org/W2112420033","https://openalex.org/W2113922211","https://openalex.org/W2135263912","https://openalex.org/W2138108551","https://openalex.org/W2145339207","https://openalex.org/W2150886314","https://openalex.org/W2160541537","https://openalex.org/W2165949563","https://openalex.org/W2168405694","https://openalex.org/W2171960770","https://openalex.org/W2182342230","https://openalex.org/W2257979135","https://openalex.org/W2317700292","https://openalex.org/W2340502990","https://openalex.org/W2341171179","https://openalex.org/W2349436533","https://openalex.org/W2499002200","https://openalex.org/W2759912774","https://openalex.org/W2787933113","https://openalex.org/W2788295351","https://openalex.org/W2799544270","https://openalex.org/W2809162153","https://openalex.org/W3015856398","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W4249267926","https://openalex.org/W6630221451"],"related_works":["https://openalex.org/W2922107804","https://openalex.org/W2963185427","https://openalex.org/W4401051025","https://openalex.org/W2065296176","https://openalex.org/W2391195099","https://openalex.org/W2315999538","https://openalex.org/W187740018","https://openalex.org/W2537376277","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3,19,32,75,86,106,130],"study":[4],"a":[5,21,45,53,88],"multi-step":[6],"interactive":[7,38],"recommendation":[8,39],"problem":[9,36],"for":[10,40,58,126],"explicit-feedback":[11],"recommender":[12],"systems.":[13],"Different":[14],"from":[15],"the":[16,29,35,64,100,124,132],"existing":[17],"works,":[18],"propose":[20,87,107],"novel":[22],"user-specific":[23,77,89,102,114],"deep":[24,90],"reinforcement":[25,55],"learning":[26,56],"approach":[27,136],"to":[28,94,111],"problem.":[30],"Specifically,":[31],"first":[33],"formulate":[34],"of":[37,134],"each":[41],"target":[42],"user":[43],"as":[44],"Markov":[46],"decision":[47],"process":[48],"(MDP).":[49],"We":[50],"then":[51],"derive":[52],"multi-MDP":[54],"task":[57],"all":[59],"involved":[60],"users.":[61,128],"To":[62],"model":[63,113],"possible":[65],"relationships":[66],"(including":[67],"similarities":[68],"and":[69,141],"differences)":[70],"between":[71],"different":[72,127],"users\u2019":[73],"MDPs,":[74],"construct":[76],"latent":[78,103],"states":[79],"by":[80,116,137],"using":[81],"matrix":[82],"factorization.":[83],"After":[84],"that,":[85],"Q-learning":[91],"(UDQN)":[92],"method":[93],"estimate":[95],"optimal":[96],"policies":[97],"based":[98],"on":[99],"constructed":[101],"states.":[104],"Furthermore,":[105],"Biased":[108],"UDQN":[109],"(BUDQN)":[110],"explicitly":[112],"information":[115],"employing":[117],"an":[118],"additional":[119],"bias":[120],"parameter":[121],"when":[122],"estimating":[123],"Q-values":[125],"Finally,":[129],"validate":[131],"effectiveness":[133],"our":[135],"comprehensive":[138],"experimental":[139],"results":[140],"analysis.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}