{"id":"https://openalex.org/W2989067042","doi":"https://doi.org/10.1145/3357384.3357945","title":"Context-Aware Ranking by Constructing a Virtual Environment for Reinforcement Learning","display_name":"Context-Aware Ranking by Constructing a Virtual Environment for Reinforcement Learning","publication_year":2019,"publication_date":"2019-11-03","ids":{"openalex":"https://openalex.org/W2989067042","doi":"https://doi.org/10.1145/3357384.3357945","mag":"2989067042"},"language":"en","primary_location":{"id":"doi:10.1145/3357384.3357945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3357945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","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/A5100648252","display_name":"Junqi Zhang","orcid":"https://orcid.org/0000-0002-6234-8171"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junqi Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072119199","display_name":"Jiaxin Mao","orcid":"https://orcid.org/0000-0002-9257-5498"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Mao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668121","display_name":"Yiqun Liu","orcid":"https://orcid.org/0000-0002-0140-4512"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqun Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003393009","display_name":"Ruizhe Zhang","orcid":"https://orcid.org/0000-0002-6937-7653"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruizhe Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402996","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0003-3158-1920"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760812","display_name":"Shaoping Ma","orcid":"https://orcid.org/0000-0002-8762-8268"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoping Ma","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020766468","display_name":"Jun Xu","orcid":"https://orcid.org/0000-0001-7170-111X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393506","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0002-7252-5047"},"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":"Qi Tian","raw_affiliation_strings":["Huawei Noah's Ark Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100648252"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.6957,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88689758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1603","last_page":"1612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9939000010490417,"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":0.9939000010490417,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9915000200271606,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9904999732971191,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8341163396835327},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7761379480361938},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.6905274391174316},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6280100345611572},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5806125998497009},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5532057285308838},{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.5262736082077026},{"id":"https://openalex.org/keywords/ranking-svm","display_name":"Ranking SVM","score":0.49405696988105774},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4883953928947449},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.45915427803993225},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4311942458152771},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.42158043384552},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37895411252975464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36598122119903564},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.260698139667511}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341163396835327},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7761379480361938},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.6905274391174316},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6280100345611572},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5806125998497009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5532057285308838},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.5262736082077026},{"id":"https://openalex.org/C124975894","wikidata":"https://www.wikidata.org/wiki/Q7293290","display_name":"Ranking SVM","level":3,"score":0.49405696988105774},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4883953928947449},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.45915427803993225},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4311942458152771},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.42158043384552},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37895411252975464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36598122119903564},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.260698139667511},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3357384.3357945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3357945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W213343370","https://openalex.org/W1625390266","https://openalex.org/W1968927634","https://openalex.org/W2005084129","https://openalex.org/W2007815473","https://openalex.org/W2026784708","https://openalex.org/W2047952076","https://openalex.org/W2056044004","https://openalex.org/W2061562262","https://openalex.org/W2069870183","https://openalex.org/W2083305840","https://openalex.org/W2096438175","https://openalex.org/W2099213975","https://openalex.org/W2102693936","https://openalex.org/W2121615981","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2154739689","https://openalex.org/W2163421455","https://openalex.org/W2170051049","https://openalex.org/W2179488730","https://openalex.org/W2257979135","https://openalex.org/W2339829457","https://openalex.org/W2396229782","https://openalex.org/W2580175322","https://openalex.org/W2740384884","https://openalex.org/W2797400361","https://openalex.org/W2798492560","https://openalex.org/W2798835721","https://openalex.org/W2799226155","https://openalex.org/W2884349765","https://openalex.org/W2897496397","https://openalex.org/W2955037254","https://openalex.org/W2963654596","https://openalex.org/W2964199361","https://openalex.org/W2997842202","https://openalex.org/W3103497827","https://openalex.org/W3138773240","https://openalex.org/W4234617775","https://openalex.org/W6753306234"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W85699040"],"abstract_inverted_index":{"Result":[0],"ranking":[1,55,65,81,89,119,177],"is":[2,91],"one":[3],"of":[4,26,117,128,136,167],"the":[5,30,102,108,115,118,134,157,171],"major":[6],"concerns":[7],"for":[8],"Web":[9],"search":[10,16,35,43,176],"technologies.":[11],"Most":[12],"existing":[13],"methodologies":[14],"rank":[15],"results":[17,36],"in":[18],"descending":[19],"order":[20],"according":[21],"to":[22,77,111,132],"pointwise":[23],"relevance":[24],"estimation":[25],"single":[27],"results.":[28],"However,":[29],"dependency":[31],"relationship":[32],"between":[33],"different":[34],"are":[37],"not":[38],"taken":[39],"into":[40],"account.":[41],"While":[42],"engine":[44],"result":[45,64],"pages":[46],"contain":[47],"more":[48,50],"and":[49,62,99,144,162],"heterogenous":[51],"components,":[52],"a":[53,59,72,94,123,151,180],"better":[54],"strategy":[56],"should":[57],"be":[58],"context-aware":[60,79],"process":[61],"optimize":[63],"globally.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,121],"propose":[71],"novel":[73],"framework":[74,173],"which":[75],"aims":[76],"improve":[78,175],"listwise":[80],"performance":[82,178],"by":[83,179],"optimizing":[84],"online":[85,112],"evaluation":[86],"metrics.":[87],"The":[88],"problem":[90],"formalized":[92],"as":[93],"Markov":[95],"Decision":[96],"Process":[97],"(MDP)":[98],"solved":[100],"with":[101,126],"reinforcement":[103],"learning":[104],"paradigm.":[105],"To":[106],"avoid":[107],"great":[109],"cost":[110],"systems":[113],"during":[114],"training":[116],"model,":[120],"construct":[122],"virtual":[124,152],"environment":[125,153],"millions":[127],"historical":[129],"click":[130,160],"logs":[131,161],"simulate":[133],"behavior":[135],"real":[137,145,168],"users.":[138,169],"Extensive":[139],"experiments":[140],"on":[141],"both":[142],"simulated":[143],"datasets":[146],"show":[147],"that:":[148],"1)":[149],"constructing":[150],"can":[154,174],"effectively":[155],"leverage":[156],"large":[158,181],"scale":[159],"capture":[163],"some":[164],"important":[165],"properties":[166],"2)":[170],"proposed":[172],"margin.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}