{"id":"https://openalex.org/W3163450606","doi":"https://doi.org/10.1109/csicc52343.2021.9420615","title":"Improving ranking function and diversification in interactive recommendation systems based on deep reinforcement learning","display_name":"Improving ranking function and diversification in interactive recommendation systems based on deep reinforcement learning","publication_year":2021,"publication_date":"2021-03-03","ids":{"openalex":"https://openalex.org/W3163450606","doi":"https://doi.org/10.1109/csicc52343.2021.9420615","mag":"3163450606"},"language":"en","primary_location":{"id":"doi:10.1109/csicc52343.2021.9420615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csicc52343.2021.9420615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5064550357","display_name":"Vahid Baghi","orcid":null},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Vahid Baghi","raw_affiliation_strings":["University of Tehran,Dept. of Algorithms and Computation,Tehran,Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran,Dept. of Algorithms and Computation,Tehran,Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012299359","display_name":"Seyed Mohammad Seyed Motehayeri","orcid":null},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Seyed Mohammad Seyed Motehayeri","raw_affiliation_strings":["University of Tehran,Dept. of Algorithms and Computation,Tehran,Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran,Dept. of Algorithms and Computation,Tehran,Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101930446","display_name":"Ali Moeini","orcid":"https://orcid.org/0000-0002-6408-3525"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ali Moeini","raw_affiliation_strings":["University of Tehran,Dept. of Algorithms and Computation,Tehran,Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran,Dept. of Algorithms and Computation,Tehran,Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076879409","display_name":"Rooholah Abedian","orcid":"https://orcid.org/0000-0002-1739-5964"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Rooholah Abedian","raw_affiliation_strings":["University of Tehran,Dept. of Algorithms and Computation,Tehran,Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran,Dept. of Algorithms and Computation,Tehran,Iran","institution_ids":["https://openalex.org/I23946033"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I23946033"],"apc_list":null,"apc_paid":null,"fwci":1.534,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83235493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":null,"first_page":"1","last_page":"7"},"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":0.9916999936103821,"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":0.9753999710083008,"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/movielens","display_name":"MovieLens","score":0.8760486841201782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8274915218353271},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.794744074344635},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7894723415374756},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6034871339797974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.561006486415863},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5488751530647278},{"id":"https://openalex.org/keywords/diversification","display_name":"Diversification (marketing strategy)","score":0.4705904722213745},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46918535232543945},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42198604345321655},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4175799489021301},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3220904469490051},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.25360625982284546}],"concepts":[{"id":"https://openalex.org/C2776156558","wikidata":"https://www.wikidata.org/wiki/Q4353746","display_name":"MovieLens","level":4,"score":0.8760486841201782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8274915218353271},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.794744074344635},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7894723415374756},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6034871339797974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.561006486415863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5488751530647278},{"id":"https://openalex.org/C180916674","wikidata":"https://www.wikidata.org/wiki/Q3711935","display_name":"Diversification (marketing strategy)","level":2,"score":0.4705904722213745},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46918535232543945},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42198604345321655},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4175799489021301},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3220904469490051},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.25360625982284546},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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":1,"locations":[{"id":"doi:10.1109/csicc52343.2021.9420615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csicc52343.2021.9420615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1563092753","https://openalex.org/W1991885946","https://openalex.org/W2000110130","https://openalex.org/W2024320089","https://openalex.org/W2038428842","https://openalex.org/W2083305840","https://openalex.org/W2091780923","https://openalex.org/W2097951507","https://openalex.org/W2108738385","https://openalex.org/W2112420033","https://openalex.org/W2137245235","https://openalex.org/W2138108551","https://openalex.org/W2145339207","https://openalex.org/W2155912844","https://openalex.org/W2159155347","https://openalex.org/W2173248099","https://openalex.org/W2182342230","https://openalex.org/W2215378786","https://openalex.org/W2257979135","https://openalex.org/W2604639157","https://openalex.org/W2604822632","https://openalex.org/W2757662681","https://openalex.org/W2766447205","https://openalex.org/W2781763969","https://openalex.org/W2787933113","https://openalex.org/W2788295351","https://openalex.org/W2799544270","https://openalex.org/W2810785043","https://openalex.org/W2898273872","https://openalex.org/W2921693870","https://openalex.org/W2936496719","https://openalex.org/W2949985202","https://openalex.org/W2963403868","https://openalex.org/W2963864421","https://openalex.org/W2964108915","https://openalex.org/W2990747716","https://openalex.org/W3040659409","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3138773240","https://openalex.org/W4295159762","https://openalex.org/W4385245566","https://openalex.org/W4394672593","https://openalex.org/W6630221451","https://openalex.org/W6676077707","https://openalex.org/W6680451568","https://openalex.org/W6684921986","https://openalex.org/W6686200487","https://openalex.org/W6736274000","https://openalex.org/W6739901393","https://openalex.org/W6747095738","https://openalex.org/W6753243525","https://openalex.org/W6755373136","https://openalex.org/W6760331673","https://openalex.org/W6761697856"],"related_works":["https://openalex.org/W2524663498","https://openalex.org/W2113380565","https://openalex.org/W2781850661","https://openalex.org/W4233347881","https://openalex.org/W3004286290","https://openalex.org/W2169020911","https://openalex.org/W4242809128","https://openalex.org/W2297964623","https://openalex.org/W2907069037","https://openalex.org/W2549064611"],"abstract_inverted_index":{"Recently,":[0],"interactive":[1],"recommendation":[2,17,26,54,59,78,130,174],"systems":[3],"based":[4,28,77,176],"on":[5,29,58,157,177],"reinforcement":[6,75],"learning":[7,76],"have":[8,42],"been":[9],"attended":[10],"by":[11,80,115],"researchers":[12],"due":[13],"to":[14,50,63,84,106,112,127,141,168],"the":[15,25,52,90,95,108,119,129,145,158,178],"consider":[16],"procedure":[18],"as":[19,68],"a":[20,73,170],"dynamic":[21,86],"process":[22],"and":[23,61,93,134],"update":[24],"model":[27,85,165],"immediate":[30],"user":[31],"feedback,":[32],"which":[33],"is":[34,125,166],"neglected":[35],"in":[36],"traditional":[37],"methods.":[38],"The":[39],"existing":[40],"works":[41],"two":[43],"significant":[44],"drawbacks.":[45],"Firstly,":[46],"inefficient":[47],"ranking":[48],"function":[49],"produce":[51],"Top-N":[53],"list.":[55],"Secondly,":[56],"focusing":[57],"accuracy":[60],"inattention":[62],"other":[64],"evaluation":[65],"metrics":[66],"such":[67],"diversity.":[69,135],"This":[70],"paper":[71],"proposes":[72],"deep":[74],"system":[79],"utilizing":[81,102],"Actor-Critic":[82],"architecture":[83],"users'":[87],"interaction":[88,147],"with":[89],"recommender":[91],"agent":[92],"maximize":[94],"expected":[96],"longterm":[97],"reward.":[98],"Furthermore,":[99],"we":[100,137],"propose":[101],"Spotify's":[103],"ANNoy":[104],"algorithm":[105,124],"find":[107],"most":[109],"similar":[110],"items":[111,131],"generated":[113],"action":[114],"actor-network.":[116],"After":[117],"that,":[118],"Total":[120],"Diversity":[121],"Effect":[122],"Ranking":[123],"used":[126],"generate":[128,169],"concerning":[132],"relevancy":[133],"Moreover,":[136],"apply":[138],"positional":[139],"encoding":[140],"compute":[142],"representations":[143],"of":[144],"user's":[146,179],"sequence":[148],"without":[149],"using":[150],"sequence-aligned":[151],"recurrent":[152],"neural":[153],"networks.":[154],"Extensive":[155],"experiments":[156],"MovieLens":[159],"dataset":[160],"demonstrate":[161],"that":[162],"our":[163],"proposed":[164],"able":[167],"diverse":[171],"while":[172],"relevance":[173],"list":[175],"preferences.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}