{"id":"https://openalex.org/W1991754822","doi":"https://doi.org/10.1145/2808194.2809468","title":"Learning to Reinforce Search Effectiveness","display_name":"Learning to Reinforce Search Effectiveness","publication_year":2015,"publication_date":"2015-09-22","ids":{"openalex":"https://openalex.org/W1991754822","doi":"https://doi.org/10.1145/2808194.2809468","mag":"1991754822"},"language":"en","primary_location":{"id":"doi:10.1145/2808194.2809468","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808194.2809468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 International Conference on The Theory of 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/A5061774014","display_name":"Jiyun Luo","orcid":"https://orcid.org/0009-0000-2673-0296"},"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":true,"raw_author_name":"Jiyun Luo","raw_affiliation_strings":["Georgetown University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Georgetown University, Washington, DC, USA","institution_ids":["https://openalex.org/I184565670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065121020","display_name":"Xuchu Dong","orcid":null},"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":"Xuchu Dong","raw_affiliation_strings":["Georgetown University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Georgetown University, Washington, DC, USA","institution_ids":["https://openalex.org/I184565670"]}]},{"author_position":"last","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":"Hui Yang","raw_affiliation_strings":["Georgetown University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Georgetown University, Washington, DC, USA","institution_ids":["https://openalex.org/I184565670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061774014"],"corresponding_institution_ids":["https://openalex.org/I184565670"],"apc_list":null,"apc_paid":null,"fwci":1.7258,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88118138,"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":"271","last_page":"280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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":0.9965999722480774,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9965000152587891,"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/T12288","display_name":"Optimization and Search Problems","score":0.9961000084877014,"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":0.8505911827087402},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.8270466327667236},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8262954950332642},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.676270067691803},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.6596490144729614},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.522174596786499},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.47896865010261536},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.4204738736152649},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39810752868652344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3535151481628418},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19057440757751465},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0977889895439148}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8505911827087402},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.8270466327667236},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8262954950332642},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.676270067691803},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.6596490144729614},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.522174596786499},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.47896865010261536},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.4204738736152649},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39810752868652344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3535151481628418},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19057440757751465},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0977889895439148},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2808194.2809468","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808194.2809468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 International Conference on The Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4096128873","display_name":null,"funder_award_id":"FA8750-14-2-0226","funder_id":"https://openalex.org/F4320337531","funder_display_name":"Defense Sciences Office, DARPA"},{"id":"https://openalex.org/G5281438616","display_name":null,"funder_award_id":"IIS-1453721","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337531","display_name":"Defense Sciences Office, DARPA","ror":"https://ror.org/0447fe631"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W745775011","https://openalex.org/W1513468570","https://openalex.org/W1515851193","https://openalex.org/W1542882058","https://openalex.org/W1542941925","https://openalex.org/W1545148916","https://openalex.org/W1560074431","https://openalex.org/W1584580530","https://openalex.org/W1590759229","https://openalex.org/W1609424028","https://openalex.org/W1641379095","https://openalex.org/W1646752922","https://openalex.org/W2006710607","https://openalex.org/W2028145673","https://openalex.org/W2046715600","https://openalex.org/W2049633694","https://openalex.org/W2055007736","https://openalex.org/W2069870183","https://openalex.org/W2096968458","https://openalex.org/W2107726111","https://openalex.org/W2111526438","https://openalex.org/W2112999531","https://openalex.org/W2116435975","https://openalex.org/W2116716943","https://openalex.org/W2120502844","https://openalex.org/W2121863487","https://openalex.org/W2122223050","https://openalex.org/W2123937625","https://openalex.org/W2137931117","https://openalex.org/W2152342063","https://openalex.org/W2154764394","https://openalex.org/W2165390807","https://openalex.org/W2166895795","https://openalex.org/W2170329722","https://openalex.org/W2184092497","https://openalex.org/W2215946058","https://openalex.org/W4206842331"],"related_works":["https://openalex.org/W4230197055","https://openalex.org/W4296749040","https://openalex.org/W621808327","https://openalex.org/W644007644","https://openalex.org/W2497198634","https://openalex.org/W3012257603","https://openalex.org/W1586784764","https://openalex.org/W4292264782","https://openalex.org/W1965155517","https://openalex.org/W1970949629"],"abstract_inverted_index":{"Session":[0,142],"search":[1,17,66,79,99,128,157],"is":[2,100,151],"an":[3,115],"Information":[4],"Retrieval":[5],"(IR)":[6],"task":[7],"which":[8],"handles":[9],"a":[10,16,24,34,60,68],"series":[11],"of":[12,98],"queries":[13],"issued":[14],"for":[15,154],"task.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22,63,104],"propose":[23],"novel":[25],"reinforcement":[26,49],"learning":[27,37],"style":[28],"information":[29],"retrieval":[30],"framework":[31],"and":[32,45,51,77,102,130],"develop":[33],"new":[35,61],"feedback":[36,112],"algorithm":[38,109,117,133],"to":[39,52,124,140],"model":[40],"user":[41,76,111],"feedback,":[42],"including":[43],"clicks":[44],"query":[46,120],"reformulations,":[47],"as":[48,67],"signals":[50],"generate":[53],"rewards":[54],"in":[55],"the":[56,75,78,83,86,95,119,135],"RL":[57],"framework.":[58],"From":[59],"perspective,":[62],"view":[64],"session":[65,127,156],"cooperative":[69],"game":[70],"played":[71],"between":[72,85],"two":[73,87],"agents,":[74],"engine.":[80],"We":[81,122],"study":[82],"communications":[84],"agents;":[88],"they":[89],"always":[90],"exchange":[91],"opinions":[92],"on":[93,134],"\"whether":[94,103],"current":[96],"stage":[97],"relevant\"":[101],"should":[105],"explore":[106],"now.\"":[107],"The":[108,144],"infers":[110],"models":[113],"by":[114],"EM":[116],"from":[118],"logs.":[121],"compare":[123],"several":[125],"state-of-the-art":[126],"algorithms":[129],"evaluate":[131],"our":[132,149],"most":[136],"recent":[137],"TREC":[138],"2012":[139],"2014":[141],"Tracks.":[143],"experimental":[145],"results":[146],"demonstrates":[147],"that":[148],"approach":[150],"highly":[152],"effective":[153],"improving":[155],"accuracy.":[158]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}