{"id":"https://openalex.org/W3179555038","doi":"https://doi.org/10.1145/3404835.3462813","title":"Reinforcement Learning for Information Retrieval","display_name":"Reinforcement Learning for Information Retrieval","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3179555038","doi":"https://doi.org/10.1145/3404835.3462813","mag":"3179555038"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3462813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/A5040529511","display_name":"Alexander Kuhnle","orcid":"https://orcid.org/0000-0002-2361-115X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Kuhnle","raw_affiliation_strings":["Blue Prism AI Labs, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Blue Prism AI Labs, London, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019687244","display_name":"Miguel Aroca-Ouellette","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miguel Aroca-Ouellette","raw_affiliation_strings":["Blue Prism AI Labs, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Blue Prism AI Labs, London, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112983303","display_name":"Anindya Basu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anindya Basu","raw_affiliation_strings":["Blue Prism AI Labs, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Blue Prism AI Labs, London, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064283689","display_name":"Murat \u015eensoy","orcid":"https://orcid.org/0000-0001-8806-4508"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murat Sensoy","raw_affiliation_strings":["Blue Prism AI Labs, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Blue Prism AI Labs, London, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068447187","display_name":"John E. Reid","orcid":"https://orcid.org/0000-0002-7762-6760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Reid","raw_affiliation_strings":["Blue Prism AI Labs, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Blue Prism AI Labs, London, United Kingdom","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015784640","display_name":"Dell Zhang","orcid":"https://orcid.org/0000-0002-8774-3725"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dell Zhang","raw_affiliation_strings":["Blue Prism AI Labs, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Blue Prism AI Labs, London, United Kingdom","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7337,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84705294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2669","last_page":"2672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9959999918937683,"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/T12288","display_name":"Optimization and Search Problems","score":0.9958000183105469,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8913261294364929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8501929044723511},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4992852210998535},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.475147008895874},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4684109091758728},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4289160966873169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3331260085105896}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8913261294364929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8501929044723511},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4992852210998535},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.475147008895874},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4684109091758728},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4289160966873169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3331260085105896}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404835.3462813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","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":50,"referenced_works":["https://openalex.org/W1658008008","https://openalex.org/W2033912027","https://openalex.org/W2058840575","https://openalex.org/W2061562262","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2156737235","https://openalex.org/W2165150801","https://openalex.org/W2257979135","https://openalex.org/W2474081654","https://openalex.org/W2492794003","https://openalex.org/W2557283755","https://openalex.org/W2559655401","https://openalex.org/W2614839826","https://openalex.org/W2619206542","https://openalex.org/W2739916191","https://openalex.org/W2740384884","https://openalex.org/W2759050994","https://openalex.org/W2787933113","https://openalex.org/W2788295351","https://openalex.org/W2795843265","https://openalex.org/W2883364792","https://openalex.org/W2889658777","https://openalex.org/W2902572901","https://openalex.org/W2946248329","https://openalex.org/W2963523627","https://openalex.org/W2963609889","https://openalex.org/W2970534317","https://openalex.org/W2985924367","https://openalex.org/W2987046690","https://openalex.org/W2995298643","https://openalex.org/W2996959725","https://openalex.org/W3007094061","https://openalex.org/W3011120880","https://openalex.org/W3012881846","https://openalex.org/W3025606523","https://openalex.org/W3034329167","https://openalex.org/W3034853385","https://openalex.org/W3035106673","https://openalex.org/W3043826557","https://openalex.org/W3088731664","https://openalex.org/W3099134564","https://openalex.org/W3101023724","https://openalex.org/W3102778384","https://openalex.org/W3103141630","https://openalex.org/W3154925836","https://openalex.org/W3173984942","https://openalex.org/W4206275166","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W3197542405","https://openalex.org/W2056712470","https://openalex.org/W3125580266","https://openalex.org/W4317039510","https://openalex.org/W4238861846"],"abstract_inverted_index":{"There":[0],"is":[1],"strong":[2],"interest":[3],"in":[4,20,28,89,100],"leveraging":[5],"reinforcement":[6],"learning":[7],"(RL)":[8],"for":[9,170],"information":[10],"retrieval":[11],"(IR)":[12],"applications":[13,97],"including":[14],"search,":[15],"recommendation,":[16],"and":[17,48,60,69,106,123,129,161],"advertising.":[18],"Just":[19],"2020,":[21],"the":[22,79,84,112,140,166],"term":[23],"\"reinforcement":[24],"learning\"":[25],"was":[26],"mentioned":[27],"more":[29,171],"than":[30],"60":[31],"different":[32],"papers":[33],"published":[34],"by":[35],"ACM":[36],"SIGIR.":[37],"It":[38],"has":[39],"also":[40],"been":[41],"reported":[42],"that":[43],"Internet":[44],"companies":[45],"like":[46],"Google":[47],"Alibaba":[49],"have":[50,72],"started":[51],"to":[52,81,151,165],"gain":[53],"competitive":[54],"advantages":[55],"from":[56],"their":[57,153],"RL-based":[58],"search":[59],"recommendation":[61],"engines.":[62],"This":[63,131],"full-day":[64],"tutorial":[65,167],"gives":[66],"IR":[67,101,142,156],"researchers":[68],"practitioners":[70],"who":[71],"no":[73],"or":[74],"little":[75],"experience":[76],"with":[77],"RL":[78,88,99,121,159],"opportunity":[80],"learn":[82],"about":[83],"fundamentals":[85],"of":[86,98,119,139],"modern":[87,120],"a":[90,116],"practical":[91,155],"hands-on":[92],"setting.":[93],"Furthermore,":[94],"some":[95,138],"representative":[96],"systems":[102],"will":[103,114,133],"be":[104],"introduced":[105],"discussed.":[107],"By":[108],"attending":[109],"this":[110],"tutorial,":[111],"participants":[113],"acquire":[115],"good":[117],"knowledge":[118,132],"concepts":[122],"standard":[124],"algorithms":[125],"such":[126],"as":[127,146,148],"REINFORCE":[128],"DQN.":[130],"help":[134],"them":[135,150],"better":[136],"understand":[137],"latest":[141],"publications":[143],"involving":[144],"RL,":[145],"well":[147],"prepare":[149],"tackle":[152],"own":[154],"problems":[157],"using":[158],"techniques":[160],"tools.":[162],"Please":[163],"refer":[164],"website":[168],"(https://rl-starterpack.github.io/)":[169],"information.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}