{"id":"https://openalex.org/W3191479442","doi":"https://doi.org/10.1145/3460231.3478864","title":"Sequence Adaptation via Reinforcement Learning in Recommender Systems","display_name":"Sequence Adaptation via Reinforcement Learning in Recommender Systems","publication_year":2021,"publication_date":"2021-09-13","ids":{"openalex":"https://openalex.org/W3191479442","doi":"https://doi.org/10.1145/3460231.3478864","mag":"3191479442"},"language":"en","primary_location":{"id":"doi:10.1145/3460231.3478864","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460231.3478864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.01442","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059198427","display_name":"Stefanos Antaris","orcid":"https://orcid.org/0000-0002-1135-8863"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Stefanos Antaris","raw_affiliation_strings":["KTH Royal Institute of Technology, Sweden","KTH, Royal Inst. of Technology, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH, Royal Inst. of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034151597","display_name":"Dimitrios Rafailidis","orcid":"https://orcid.org/0000-0002-7366-3716"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios Rafailidis","raw_affiliation_strings":["University of Thessaly, Greece","University Of Thessaly, Greece"],"affiliations":[{"raw_affiliation_string":"University of Thessaly, Greece","institution_ids":["https://openalex.org/I145722265"]},{"raw_affiliation_string":"University Of Thessaly, Greece","institution_ids":["https://openalex.org/I145722265"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059198427"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16051257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"714","last_page":"718"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9987999796867371,"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":0.9940000176429749,"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/computer-science","display_name":"Computer science","score":0.8256900906562805},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7250746488571167},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6975980401039124},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6283383369445801},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5694788098335266},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5671381950378418},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5640281438827515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4743025302886963},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4739396870136261},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45998305082321167},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.45441943407058716},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45089203119277954},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.4365497827529907},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4241909384727478},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32735493779182434},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1903117597103119},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10152843594551086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256900906562805},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7250746488571167},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6975980401039124},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6283383369445801},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5694788098335266},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5671381950378418},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5640281438827515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4743025302886963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4739396870136261},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45998305082321167},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.45441943407058716},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45089203119277954},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.4365497827529907},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4241909384727478},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32735493779182434},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1903117597103119},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10152843594551086},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3460231.3478864","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460231.3478864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth ACM Conference on Recommender Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.01442","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.01442","pdf_url":"https://arxiv.org/pdf/2108.01442","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3191479442","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2108.01442","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2108.01442","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2108.01442","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.01442","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.01442","pdf_url":"https://arxiv.org/pdf/2108.01442","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3191479442.pdf","grobid_xml":"https://content.openalex.org/works/W3191479442.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2121863487","https://openalex.org/W2156737235","https://openalex.org/W2605341677","https://openalex.org/W2626454364","https://openalex.org/W2908404712","https://openalex.org/W2918932727","https://openalex.org/W2946617802","https://openalex.org/W2963403868","https://openalex.org/W2963704132","https://openalex.org/W2964108915","https://openalex.org/W2964121744","https://openalex.org/W2964316331","https://openalex.org/W2965744319","https://openalex.org/W2970345470","https://openalex.org/W2985880542","https://openalex.org/W2996931760","https://openalex.org/W2998167534","https://openalex.org/W3005071803","https://openalex.org/W3017258201","https://openalex.org/W3034853385","https://openalex.org/W3035435378","https://openalex.org/W3045525389","https://openalex.org/W3049332778","https://openalex.org/W3088203142","https://openalex.org/W3094595891","https://openalex.org/W3097907450","https://openalex.org/W3100480425","https://openalex.org/W3102848167","https://openalex.org/W3103248659","https://openalex.org/W3105879597","https://openalex.org/W6823560597"],"related_works":["https://openalex.org/W3199047808","https://openalex.org/W2942107503","https://openalex.org/W3100917752","https://openalex.org/W3208636516","https://openalex.org/W3129523363","https://openalex.org/W3084418435","https://openalex.org/W3178598966","https://openalex.org/W2978133183","https://openalex.org/W2970345470","https://openalex.org/W3118697270","https://openalex.org/W3135529416","https://openalex.org/W2949390961","https://openalex.org/W3101314357","https://openalex.org/W2908414126","https://openalex.org/W2186109963","https://openalex.org/W2625490831","https://openalex.org/W3035029760","https://openalex.org/W3131701661","https://openalex.org/W2990162188","https://openalex.org/W3089174246"],"abstract_inverted_index":{"Accounting":[0],"for":[1],"the":[2,10,32,37,48,63,70,85,92,98,115,121,129,148,151,155,160,165,170,174,189],"fact":[3],"that":[4,18],"users":[5,43],"have":[6],"different":[7,45],"sequential":[8,49,57,74,93,152],"patterns,":[9],"main":[11],"drawback":[12],"of":[13,23,72,101,150,159,191],"state-of-the-art":[14],"recommendation":[15,38],"strategies":[16,53],"is":[17,26],"a":[19,105,134,142,178],"fixed":[20],"sequence":[21,99,123,171],"length":[22,100,124,172],"user-item":[24,102],"interactions":[25,58,103],"required":[27],"as":[28,40,125],"input":[29],"to":[30,62,119,146],"train":[31],"models.":[33],"This":[34],"might":[35,54],"limit":[36],"accuracy,":[39],"in":[41,80,104,177],"practice":[42],"follow":[44],"trends":[46],"on":[47,69,184],"recommendations.":[50],"Hence,":[51],"baseline":[52,197],"ignore":[55],"important":[56],"or":[59],"add":[60],"noise":[61],"models":[64],"with":[65,154,173],"redundant":[66],"interactions,":[67],"depending":[68],"variety":[71],"users'":[73],"behaviours.":[75],"To":[76],"overcome":[77],"this":[78,81],"problem,":[79],"study":[82],"we":[83,140,168,200],"propose":[84],"SAR":[86],"model,":[87],"which":[88],"not":[89],"only":[90],"learns":[91],"patterns":[94],"but":[95],"also":[96],"adjusts":[97],"personalized":[106,179],"manner.":[107,180],"We":[108],"first":[109],"design":[110],"an":[111,126],"actor-critic":[112],"framework,":[113],"where":[114],"RL":[116],"agent":[117],"tries":[118],"compute":[120],"optimal":[122],"action,":[127],"given":[128],"user's":[130],"state":[131],"representation":[132],"at":[133,164,206],"certain":[135],"time":[136,167],"step.":[137],"In":[138],"addition,":[139],"optimize":[141],"joint":[143],"loss":[144],"function":[145],"align":[147],"accuracy":[149],"recommendations":[153],"expected":[156],"cumulative":[157],"rewards":[158],"critic":[161],"network,":[162],"while":[163],"same":[166],"adapt":[169],"actor":[175],"network":[176],"Our":[181],"experimental":[182],"evaluation":[183],"four":[185],"real-world":[186],"datasets":[187],"demonstrates":[188],"superiority":[190],"our":[192,202],"proposed":[193],"model":[194],"over":[195],"several":[196],"approaches.":[198],"Finally,":[199],"make":[201],"implementation":[203],"publicly":[204],"available":[205],"https://github.com/stefanosantaris/sar.":[207]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}