{"id":"https://openalex.org/W4300006470","doi":"https://doi.org/10.21428/594757db.6a36bb36","title":"Sample Efficiency in Deep Reinforcement Learning based Recommender Systems with Imitation Learning","display_name":"Sample Efficiency in Deep Reinforcement Learning based Recommender Systems with Imitation Learning","publication_year":2022,"publication_date":"2022-05-27","ids":{"openalex":"https://openalex.org/W4300006470","doi":"https://doi.org/10.21428/594757db.6a36bb36"},"language":"en","primary_location":{"id":"doi:10.21428/594757db.6a36bb36","is_oa":true,"landing_page_url":"https://doi.org/10.21428/594757db.6a36bb36","pdf_url":"https://caiac.pubpub.org/pub/d0jo6snj/download/pdf","source":null,"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 Canadian Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://caiac.pubpub.org/pub/d0jo6snj/download/pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110766111","display_name":"Mohammad Mehdi Afsar","orcid":null},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mohammad Mehdi Afsar","raw_affiliation_strings":["University of Calgary"],"affiliations":[{"raw_affiliation_string":"University of Calgary","institution_ids":["https://openalex.org/I168635309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042659974","display_name":"Trafford Crump","orcid":"https://orcid.org/0000-0001-6690-1926"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Trafford Crump","raw_affiliation_strings":["University of Calgary"],"affiliations":[{"raw_affiliation_string":"University of Calgary","institution_ids":["https://openalex.org/I168635309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008779348","display_name":"Behrouz H. Far","orcid":"https://orcid.org/0000-0003-1589-8039"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Behrouz Far","raw_affiliation_strings":["University of Calgary"],"affiliations":[{"raw_affiliation_string":"University of Calgary","institution_ids":["https://openalex.org/I168635309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110766111"],"corresponding_institution_ids":["https://openalex.org/I168635309"],"apc_list":null,"apc_paid":null,"fwci":0.1388,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55414774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.977400004863739,"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":0.977400004863739,"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":0.9681000113487244,"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":0.9466999769210815,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9277322292327881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8129330277442932},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.793404221534729},{"id":"https://openalex.org/keywords/rss","display_name":"RSS","score":0.7841468453407288},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.7376975417137146},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6349974274635315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6122795343399048},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.515252411365509},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5046130418777466},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43923380970954895},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09139791131019592},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06823667883872986}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9277322292327881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8129330277442932},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.793404221534729},{"id":"https://openalex.org/C2385561","wikidata":"https://www.wikidata.org/wiki/Q45432","display_name":"RSS","level":2,"score":0.7841468453407288},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7376975417137146},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6349974274635315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122795343399048},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.515252411365509},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5046130418777466},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43923380970954895},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09139791131019592},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06823667883872986},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21428/594757db.6a36bb36","is_oa":true,"landing_page_url":"https://doi.org/10.21428/594757db.6a36bb36","pdf_url":"https://caiac.pubpub.org/pub/d0jo6snj/download/pdf","source":null,"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 Canadian Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.21428/594757db.6a36bb36","is_oa":true,"landing_page_url":"https://doi.org/10.21428/594757db.6a36bb36","pdf_url":"https://caiac.pubpub.org/pub/d0jo6snj/download/pdf","source":null,"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 Canadian Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4300006470.pdf","grobid_xml":"https://content.openalex.org/works/W4300006470.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W5432481","https://openalex.org/W41554520","https://openalex.org/W1486317198","https://openalex.org/W1522301498","https://openalex.org/W1597703625","https://openalex.org/W2012516036","https://openalex.org/W2054141820","https://openalex.org/W2069870183","https://openalex.org/W2116206254","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2386126672","https://openalex.org/W2580175322","https://openalex.org/W2741122588","https://openalex.org/W2754517384","https://openalex.org/W2756826236","https://openalex.org/W2788295351","https://openalex.org/W2788862220","https://openalex.org/W2919013397","https://openalex.org/W2952955766","https://openalex.org/W2963099939","https://openalex.org/W2984869362","https://openalex.org/W3011120880","https://openalex.org/W3029587262","https://openalex.org/W3034833075","https://openalex.org/W3035166059","https://openalex.org/W3040094401","https://openalex.org/W3043995487","https://openalex.org/W3090856795","https://openalex.org/W3099726771","https://openalex.org/W3103559770","https://openalex.org/W3106445281","https://openalex.org/W3116249021","https://openalex.org/W3122507327","https://openalex.org/W3123348991","https://openalex.org/W3160543801","https://openalex.org/W3163545724","https://openalex.org/W3164255383","https://openalex.org/W3169528684","https://openalex.org/W3194194466","https://openalex.org/W3206324923","https://openalex.org/W4244404635","https://openalex.org/W6600280466","https://openalex.org/W6600388300","https://openalex.org/W6601798204","https://openalex.org/W6602287985","https://openalex.org/W6628852674","https://openalex.org/W6635790205","https://openalex.org/W6653708959","https://openalex.org/W6655799757","https://openalex.org/W6687681856","https://openalex.org/W6744123322","https://openalex.org/W6748645729","https://openalex.org/W6802356573"],"related_works":["https://openalex.org/W4294023446","https://openalex.org/W3177075132","https://openalex.org/W2991420365","https://openalex.org/W3036063733","https://openalex.org/W2995703874","https://openalex.org/W4386728798","https://openalex.org/W4300006470","https://openalex.org/W4319083788","https://openalex.org/W4287389313","https://openalex.org/W3123348991"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2],"been":[3],"an":[4],"unprecedented":[5],"interest":[6],"in":[7,21,39,112],"using":[8],"reinforcement":[9],"learning":[10,59,69],"(RL)":[11],"for":[12],"recommender":[13],"systems":[14],"(RSs),":[15],"due":[16],"to":[17,42,64,70,110],"its":[18,88],"unique":[19],"ability":[20],"taking":[22],"into":[23],"account":[24],"the":[25],"dynamic":[26,46],"and":[27,48,91],"long-term":[28],"user":[29,80],"engagement.":[30],"However,":[31],"sample":[32],"ine":[33],"ciency":[34],"is":[35],"a":[36],"major":[37],"challenge":[38],"applying":[40],"RL":[41,66],"problems":[43],"with":[44,67],"very":[45],"environments":[47],"huge":[49],"actions":[50],"spaces.":[51],"In":[52],"this":[53,72],"paper,":[54],"we":[55,82],"present":[56],"Imitation,":[57],"Reinforcement":[58],"based":[60],"Recommender":[61],"System":[62],"(IR2S)":[63],"combine":[65],"imitation":[68],"alleviate":[71],"problem.":[73],"Morespeci":[74],"cally,":[75],"by":[76],"utilizing":[77],"demonstrations":[78],"(available":[79],"ratings),":[81],"show":[83],"that":[84],"IR2S":[85],"can":[86],"optimize":[87],"behavior":[89],"faster":[90],"more":[92],"e":[93],"ciently.":[94],"The":[95],"proposed":[96],"IR2S,":[97],"built":[98],"on":[99],"top":[100],"of":[101],"Deep":[102],"Q":[103],"Network":[104],"(DQN),":[105],"shows":[106],"superior":[107],"performance":[108],"compared":[109],"baselines":[111],"experiments.":[113]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}