{"id":"https://openalex.org/W4386728944","doi":"https://doi.org/10.1145/3604915.3608855","title":"Deep Exploration for Recommendation Systems","display_name":"Deep Exploration for Recommendation Systems","publication_year":2023,"publication_date":"2023-09-14","ids":{"openalex":"https://openalex.org/W4386728944","doi":"https://doi.org/10.1145/3604915.3608855"},"language":"en","primary_location":{"id":"doi:10.1145/3604915.3608855","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604915.3608855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM Conference on Recommender Systems","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":null,"display_name":"Zheqing Zhu","orcid":"https://orcid.org/0000-0002-1162-106X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zheqing Zhu","raw_affiliation_strings":["Applied Reinforcement Learning, Meta AI, USA and Stanford University, USA"],"raw_orcid":"https://orcid.org/0000-0002-1162-106X","affiliations":[{"raw_affiliation_string":"Applied Reinforcement Learning, Meta AI, USA and Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045543562","display_name":"Benjamin Van Roy","orcid":"https://orcid.org/0000-0001-8364-3746"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Van Roy","raw_affiliation_strings":["Stanford University, USA"],"raw_orcid":"https://orcid.org/0000-0001-8364-3746","affiliations":[{"raw_affiliation_string":"Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.2328,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81557551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"963","last_page":"970"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9973999857902527,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9866999983787537,"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":0.7959390878677368},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6427474021911621},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6083745956420898},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5828022360801697},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5494517683982849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5315040946006775},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5084342360496521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7959390878677368},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6427474021911621},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6083745956420898},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5828022360801697},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5494517683982849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5315040946006775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5084342360496521},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3604915.3608855","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604915.3608855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2039522160","https://openalex.org/W2042636099","https://openalex.org/W2098943122","https://openalex.org/W2108081061","https://openalex.org/W2112420033","https://openalex.org/W2125880343","https://openalex.org/W2168405694","https://openalex.org/W2475334473","https://openalex.org/W2604960773","https://openalex.org/W2741951152","https://openalex.org/W2787933113","https://openalex.org/W2790360016","https://openalex.org/W2891447705","https://openalex.org/W2902572901","https://openalex.org/W2948345531","https://openalex.org/W2962712142","https://openalex.org/W2962745591","https://openalex.org/W2963654596","https://openalex.org/W2970793364","https://openalex.org/W2973198305","https://openalex.org/W2974778612","https://openalex.org/W3008155176","https://openalex.org/W3096831136","https://openalex.org/W4296604485"],"related_works":["https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W3092950680","https://openalex.org/W4246980185","https://openalex.org/W2150182025","https://openalex.org/W3197542405","https://openalex.org/W2418190244","https://openalex.org/W4238861846","https://openalex.org/W3125580266","https://openalex.org/W4380075502"],"abstract_inverted_index":{"Modern":[0],"recommendation":[1,94,100],"systems":[2],"ought":[3],"to":[4,17,25,51,66],"benefit":[5],"by":[6],"probing":[7,65,74],"for":[8,64,75,93],"and":[9,36,106,124],"learning":[10,20,40],"from":[11,21,41,53],"delayed":[12,69,76],"feedback.":[13,70],"Research":[14],"has":[15,49,57],"tended":[16],"focus":[18],"on":[19],"a":[22,26,59,102],"user\u2019s":[23,43],"response":[24],"single":[27],"recommendation.":[28],"Such":[29],"work,":[30],"which":[31],"leverages":[32],"methods":[33,63,92],"of":[34,61,109],"supervised":[35],"bandit":[37],"learning,":[38],"forgoes":[39],"the":[42],"subsequent":[44,54],"behavior.":[45],"Where":[46],"past":[47],"work":[48],"aimed":[50],"learn":[52],"behavior,":[55],"there":[56],"been":[58],"lack":[60],"effective":[62],"elicit":[67],"informative":[68],"Effective":[71],"exploration":[72,91,111],"through":[73],"feedback":[77],"becomes":[78],"particularly":[79],"challenging":[80],"when":[81],"rewards":[82],"are":[83,117],"sparse.":[84],"To":[85],"address":[86],"this,":[87],"we":[88,98],"develop":[89],"deep":[90,110],"systems.":[95],"In":[96],"particular,":[97],"formulate":[99],"as":[101],"sequential":[103],"decision":[104],"problem":[105],"demonstrate":[107],"benefits":[108],"over":[112,128],"single-step":[113],"exploration.":[114],"Our":[115],"experiments":[116],"carried":[118],"out":[119],"with":[120],"high-fidelity":[121],"industrial-grade":[122],"simulators":[123],"establish":[125],"large":[126],"improvements":[127],"existing":[129],"algorithms.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
