{"id":"https://openalex.org/W2997914278","doi":"https://doi.org/10.1145/3336191.3371858","title":"End-to-End Deep Reinforcement Learning based Recommendation with Supervised Embedding","display_name":"End-to-End Deep Reinforcement Learning based Recommendation with Supervised Embedding","publication_year":2020,"publication_date":"2020-01-20","ids":{"openalex":"https://openalex.org/W2997914278","doi":"https://doi.org/10.1145/3336191.3371858","mag":"2997914278"},"language":"en","primary_location":{"id":"doi:10.1145/3336191.3371858","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3336191.3371858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Web Search and Data Mining","raw_type":"proceedings-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/A5100415354","display_name":"Feng Liu","orcid":"https://orcid.org/0009-0002-4079-8662"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng Liu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019541869","display_name":"Huifeng Guo","orcid":"https://orcid.org/0000-0002-7393-8994"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huifeng Guo","raw_affiliation_strings":["Noah's Ark Lab, Huawei, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Noah's Ark Lab, Huawei, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063318300","display_name":"Xutao Li","orcid":"https://orcid.org/0000-0003-1894-984X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xutao Li","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054330014","display_name":"Ruiming Tang","orcid":"https://orcid.org/0000-0002-9224-2431"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiming Tang","raw_affiliation_strings":["Noah's Ark Lab, Huawei, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Noah's Ark Lab, Huawei, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113535236","display_name":"Yunming Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunming Ye","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083350101","display_name":"Xiuqiang He","orcid":"https://orcid.org/0000-0002-4115-8205"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuqiang He","raw_affiliation_strings":["Noah's Ark Lab, Huawei, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Noah's Ark Lab, Huawei, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100415354"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":9.0749,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.9785781,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"384","last_page":"392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9968000054359436,"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":0.963699996471405,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8554204702377319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8064901828765869},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.662165641784668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6362844705581665},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5942295789718628},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5705650448799133},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5448983311653137},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5390611886978149},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.47495412826538086}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8554204702377319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8064901828765869},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.662165641784668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6362844705581665},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5942295789718628},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5705650448799133},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5448983311653137},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5390611886978149},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.47495412826538086},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3336191.3371858","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3336191.3371858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4505793484","display_name":null,"funder_award_id":"61972111,61602132,U1836107","funder_id":"https://openalex.org/F4320327720","funder_display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320327720","display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1994389483","https://openalex.org/W2044672016","https://openalex.org/W2054141820","https://openalex.org/W2074694452","https://openalex.org/W2108738385","https://openalex.org/W2112420033","https://openalex.org/W2117311203","https://openalex.org/W2126552603","https://openalex.org/W2127480961","https://openalex.org/W2137245235","https://openalex.org/W2156738026","https://openalex.org/W2215378786","https://openalex.org/W2257979135","https://openalex.org/W2312609093","https://openalex.org/W2358698356","https://openalex.org/W2470873417","https://openalex.org/W2475334473","https://openalex.org/W2509235963","https://openalex.org/W2532022121","https://openalex.org/W2553303224","https://openalex.org/W2604662567","https://openalex.org/W2723293840","https://openalex.org/W2787933113","https://openalex.org/W2788125442","https://openalex.org/W2788295351","https://openalex.org/W2799544270","https://openalex.org/W2807021761","https://openalex.org/W2902572901","https://openalex.org/W2911760887","https://openalex.org/W2950133940","https://openalex.org/W2963544079","https://openalex.org/W2963924287","https://openalex.org/W3098024612","https://openalex.org/W3100848837","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3103752844"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W1978572805","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W2383807498","https://openalex.org/W3197542405","https://openalex.org/W2056712470","https://openalex.org/W3125580266"],"abstract_inverted_index":{"The":[0,26],"research":[1],"of":[2,110,173],"reinforcement":[3],"learning":[4,140,150],"(RL)":[5],"based":[6,141,191],"recommendation":[7,15,29],"method":[8],"has":[9],"become":[10],"a":[11,35,73,83,148],"hot":[12],"topic":[13],"in":[14,22,115,123,131,189],"community,":[16],"due":[17],"to":[18,106,160,180],"the":[19,62,70,116,124,129,157,171,178,182,186,202,205,210],"recent":[20],"advance":[21],"interactive":[23],"recommender":[24],"systems.":[25],"existing":[27],"RL":[28,190,219],"approaches":[30,81],"can":[31],"be":[32,58],"summarized":[33],"into":[34],"unified":[36],"framework":[37,143],"with":[38,61],"three":[39,163,187,198],"components,":[40],"namely":[41],"embedding":[42],"component":[43,47,51],"(EC),":[44],"state":[45],"representation":[46],"(SRC)":[48],"and":[49,75,91,101,112,162,168,201,217,221],"policy":[50],"(PC).":[52],"We":[53],"find":[54],"that":[55],"EC":[56,93],"cannot":[57],"nicely":[59],"trained":[60],"other":[63],"two":[64,96],"components":[65,188],"simultaneously.":[66],"Previous":[67],"studies":[68],"bypass":[69],"obstacle":[71],"through":[72],"pre-training":[74],"fixing":[76],"strategy,":[77],"which":[78],"makes":[79],"their":[80],"unlike":[82],"real":[84],"end-to-end":[85,211],"fashion.":[86],"More":[87],"importantly,":[88],"such":[89],"pre-trained":[90],"fixed":[92,102],"suffers":[94],"from":[95],"inherent":[97],"drawbacks:":[98],"(1)":[99],"Pre-trained":[100],"embeddings":[103],"are":[104,166,177,195],"unable":[105],"model":[107],"evolving":[108],"preference":[109],"users":[111],"item":[113],"correlations":[114],"dynamic":[117],"environment;":[118],"(2)":[119],"Pre-training":[120],"is":[121,152],"inconvenient":[122],"industrial":[125],"applications.":[126],"To":[127,170],"address":[128,181],"problem,":[130],"this":[132,146],"paper,":[133],"we":[134,176],"propose":[135],"an":[136],"End-to-end":[137],"Deep":[138],"Reinforcement":[139],"Recommendation":[142],"(EDRR).":[144],"In":[145],"framework,":[147],"supervised":[149],"signal":[151],"carefully":[153],"designed":[154],"for":[155,214],"smoothing":[156],"update":[158],"gradients":[159],"EC,":[161],"incorporating":[164],"ways":[165],"introduced":[167],"compared.":[169],"best":[172],"our":[174],"knowledge,":[175],"first":[179],"training":[183,212],"compatibility":[184],"between":[185],"recommendations.":[192],"Extensive":[193],"experiments":[194],"conducted":[196],"on":[197],"real-world":[199],"datasets,":[200],"results":[203],"demonstrate":[204],"proposed":[206],"EDRR":[207],"effectively":[208],"achieves":[209],"purpose":[213],"both":[215],"policy-based":[216],"value-based":[218],"models,":[220],"delivers":[222],"better":[223],"performance":[224],"than":[225],"state-of-the-art":[226],"methods.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}