{"id":"https://openalex.org/W3043826557","doi":"https://doi.org/10.1145/3397271.3401467","title":"Deep Reinforcement Learning for Information Retrieval: Fundamentals and Advances","display_name":"Deep Reinforcement Learning for Information Retrieval: Fundamentals and Advances","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3043826557","doi":"https://doi.org/10.1145/3397271.3401467","mag":"3043826557"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401467","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3397271.3401467","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3397271.3401467","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3397271.3401467","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090720315","display_name":"Weinan Zhang","orcid":"https://orcid.org/0000-0002-0127-2425"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weinan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645854","display_name":"Xiangyu Zhao","orcid":"https://orcid.org/0000-0003-2926-4416"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhao","raw_affiliation_strings":["Michigan State University, Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Michigan State University, Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032277491","display_name":"Zhao Li","orcid":"https://orcid.org/0000-0002-5056-0351"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054482111","display_name":"Dawei Yin","orcid":"https://orcid.org/0000-0002-8846-2001"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dawei Yin","raw_affiliation_strings":["Baidu, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Baidu, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002485529","display_name":"Grace Hui Yang","orcid":"https://orcid.org/0000-0001-6095-8358"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grace Hui Yang","raw_affiliation_strings":["Georgetown University, Washington DC, DC, USA"],"affiliations":[{"raw_affiliation_string":"Georgetown University, Washington DC, DC, USA","institution_ids":["https://openalex.org/I184565670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080988309","display_name":"Alex Beutel","orcid":"https://orcid.org/0000-0002-5917-2849"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Beutel","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5090720315"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":7.2441,"has_fulltext":true,"cited_by_count":52,"citation_normalized_percentile":{"value":0.97248547,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2468","last_page":"2471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9955999851226807,"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":0.9955999851226807,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8207861185073853},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.805557131767273},{"id":"https://openalex.org/keywords/information-overload","display_name":"Information overload","score":0.7129327654838562},{"id":"https://openalex.org/keywords/cognitive-models-of-information-retrieval","display_name":"Cognitive models of information retrieval","score":0.5211958289146423},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4818626344203949},{"id":"https://openalex.org/keywords/human\u2013computer-information-retrieval","display_name":"Human\u2013computer information retrieval","score":0.474120169878006},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.40676969289779663},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38633832335472107},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32743996381759644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2933637499809265},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.23250937461853027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207861185073853},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.805557131767273},{"id":"https://openalex.org/C186625053","wikidata":"https://www.wikidata.org/wiki/Q1130191","display_name":"Information overload","level":2,"score":0.7129327654838562},{"id":"https://openalex.org/C21025794","wikidata":"https://www.wikidata.org/wiki/Q5141219","display_name":"Cognitive models of information retrieval","level":4,"score":0.5211958289146423},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4818626344203949},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.474120169878006},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40676969289779663},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38633832335472107},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32743996381759644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2933637499809265},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.23250937461853027}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3397271.3401467","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3397271.3401467","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3397271.3401467","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3397271.3401467","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3397271.3401467","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3397271.3401467","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G129499350","display_name":null,"funder_award_id":"61632017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2702356746","display_name":null,"funder_award_id":"61702","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3256823474","display_name":null,"funder_award_id":"61702327","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4433206528","display_name":null,"funder_award_id":"61772333","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8605162970","display_name":null,"funder_award_id":"61632017, 61702327, 61772333","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8955107213","display_name":null,"funder_award_id":"Major","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3043826557.pdf","grobid_xml":"https://content.openalex.org/works/W3043826557.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1967675625","https://openalex.org/W2001071536","https://openalex.org/W2058840575","https://openalex.org/W2077902449","https://openalex.org/W2091780923","https://openalex.org/W2092092836","https://openalex.org/W2099799055","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2134150392","https://openalex.org/W2138108551","https://openalex.org/W2168405694","https://openalex.org/W2169728355","https://openalex.org/W2227909145","https://openalex.org/W2358698356","https://openalex.org/W2562337727","https://openalex.org/W2583596000","https://openalex.org/W2739916191","https://openalex.org/W2740384884","https://openalex.org/W2766447205","https://openalex.org/W2788125442","https://openalex.org/W2788295351","https://openalex.org/W2788991205","https://openalex.org/W2798369493","https://openalex.org/W2799544270","https://openalex.org/W2887653292","https://openalex.org/W2902572901","https://openalex.org/W2951274974","https://openalex.org/W2963619374","https://openalex.org/W2963924287","https://openalex.org/W2964043796","https://openalex.org/W3011120880","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3103752844","https://openalex.org/W3105140685","https://openalex.org/W4210896998","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2530055068","https://openalex.org/W1987750820","https://openalex.org/W2073085562","https://openalex.org/W2047830640","https://openalex.org/W1484057680","https://openalex.org/W2115159944","https://openalex.org/W2440419249","https://openalex.org/W2162528941","https://openalex.org/W2040524271","https://openalex.org/W1717702867"],"abstract_inverted_index":{"Information":[0],"retrieval":[1,50,96,104],"(IR)":[2],"techniques,":[3,97,158],"such":[4],"as":[5],"search,":[6],"recommendation":[7],"and":[8,27,47,56,111,133,142,149,159],"online":[9],"advertising,":[10],"satisfying":[11],"users'":[12,108],"information":[13,36,49,95,103,147,165],"needs":[14],"by":[15],"suggesting":[16],"users":[17],"personalized":[18],"objects":[19],"(information":[20],"or":[21],"services)":[22],"at":[23],"the":[24,35,40,102,113,139],"appropriate":[25],"time":[26],"place,":[28],"play":[29],"a":[30,63,125],"crucial":[31,64],"role":[32],"in":[33,81,91],"mitigating":[34],"overload":[37],"problem.":[38],"Since":[39],"widely":[41],"use":[42],"of":[43,144,162],"mobile":[44],"applications,":[45],"more":[46,48],"services":[51],"have":[52,87],"provided":[53],"interactive":[54,69],"functionality":[55],"products.":[57],"Thus,":[58],"learning":[59,66,84],"from":[60,118],"interaction":[61],"becomes":[62],"machine":[65],"paradigm":[67],"for":[68,146],"IR,":[70],"which":[71,98,127],"is":[72],"based":[73,94],"on":[74,154],"reinforcement":[75,83],"learning.":[76],"With":[77],"recent":[78],"great":[79],"advances":[80],"deep":[82],"(DRL),":[85],"there":[86],"been":[88],"increasing":[89],"interests":[90],"developing":[92],"DRL":[93,145,163],"could":[99],"continuously":[100],"update":[101],"strategies":[105],"according":[106],"to":[107,123,137,151,164],"real-time":[109],"feedback,":[110],"optimize":[112],"expected":[114],"cumulative":[115],"long-term":[116],"satisfaction":[117],"users.":[119],"Our":[120],"workshop":[121],"aims":[122],"provide":[124],"venue,":[126],"can":[128],"bring":[129],"together":[130],"academia":[131],"researchers":[132],"industry":[134],"practitioners":[135],"(i)":[136],"discuss":[138],"principles,":[140],"limitations":[141],"applications":[143,161],"retrieval,":[148],"(ii)":[150],"foster":[152],"research":[153],"innovative":[155],"algorithms,":[156],"novel":[157],"new":[160],"retrieval.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}