{"id":"https://openalex.org/W3035106673","doi":"https://doi.org/10.1145/3397271.3401148","title":"Reinforcement Learning to Rank with Pairwise Policy Gradient","display_name":"Reinforcement Learning to Rank with Pairwise Policy Gradient","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3035106673","doi":"https://doi.org/10.1145/3397271.3401148","mag":"3035106673"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401148","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401148","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Jun Xu","raw_affiliation_strings":["Renmin University of China & Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China & Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101427959","display_name":"Wei Zeng","orcid":"https://orcid.org/0009-0006-4437-9042"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng Wei","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006078127","display_name":"Xia Long","orcid":"https://orcid.org/0000-0002-9705-1589"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Long Xia","raw_affiliation_strings":["York University, Toronto , Canada"],"affiliations":[{"raw_affiliation_string":"York University, Toronto , Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616866","display_name":"Yanyan Lan","orcid":"https://orcid.org/0000-0002-7811-3262"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Lan","raw_affiliation_strings":["Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054482111","display_name":"Dawei Yin","orcid":"https://orcid.org/0000-0002-8846-2001"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Yin","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025631695","display_name":"Ji-Rong Wen","orcid":"https://orcid.org/0000-0002-9777-9676"},"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":"Ji-Rong Wen","raw_affiliation_strings":["Renmin University of China & Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China & Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5020766468"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":5.8719,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.96403913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"509","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9997000098228455,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","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/T10203","display_name":"Recommender Systems and Techniques","score":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.8699572086334229},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7998247742652893},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7062236666679382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.658839225769043},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.5093454122543335},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.496161550283432},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4802672863006592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43597984313964844},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4222591817378998},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40242260694503784},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24616560339927673},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2281665802001953},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21933326125144958}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.8699572086334229},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7998247742652893},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7062236666679382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.658839225769043},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.5093454122543335},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.496161550283432},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4802672863006592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43597984313964844},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4222591817378998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40242260694503784},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24616560339927673},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2281665802001953},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21933326125144958},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3397271.3401148","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401148","pdf_url":null,"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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1973435495","https://openalex.org/W1984770088","https://openalex.org/W2007815473","https://openalex.org/W2009979684","https://openalex.org/W2023188792","https://openalex.org/W2023599408","https://openalex.org/W2047221353","https://openalex.org/W2047804176","https://openalex.org/W2047952076","https://openalex.org/W2055007736","https://openalex.org/W2067802667","https://openalex.org/W2069870183","https://openalex.org/W2079313653","https://openalex.org/W2085814658","https://openalex.org/W2104895009","https://openalex.org/W2108862644","https://openalex.org/W2115584760","https://openalex.org/W2121863487","https://openalex.org/W2125398996","https://openalex.org/W2132314908","https://openalex.org/W2138108551","https://openalex.org/W2142537246","https://openalex.org/W2143331230","https://openalex.org/W2157391629","https://openalex.org/W2171541062","https://openalex.org/W2257117461","https://openalex.org/W2337233909","https://openalex.org/W2512370135","https://openalex.org/W2619206542","https://openalex.org/W2739916191","https://openalex.org/W2740384884","https://openalex.org/W2788295351","https://openalex.org/W2797234205","https://openalex.org/W2798694866","https://openalex.org/W2798835721","https://openalex.org/W2799544270","https://openalex.org/W2889658777","https://openalex.org/W2950113463","https://openalex.org/W2962818688","https://openalex.org/W2963654596","https://openalex.org/W2963842088","https://openalex.org/W2964108915","https://openalex.org/W2990138404","https://openalex.org/W3101023724","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3138773240","https://openalex.org/W4249752786","https://openalex.org/W6628986878","https://openalex.org/W6643393412"],"related_works":["https://openalex.org/W2011472225","https://openalex.org/W3000057026","https://openalex.org/W3048565508","https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W3163984363","https://openalex.org/W2145363145"],"abstract_inverted_index":{"This":[0],"paper":[1],"concerns":[2],"reinforcement":[3],"learning~(RL)":[4],"of":[5,15,24,65,86,99,138,159],"the":[6,16,22,32,60,66,83,89,97,120,131,144,163,171,194],"document":[7,68,140,160],"ranking":[8,20,25,115],"models":[9],"for":[10],"information":[11],"retrieval~(IR).":[12],"One":[13],"branch":[14],"RL":[17],"approaches":[18,45],"to":[19,81,96,150],"formalize":[21],"process":[23],"with":[26,35,119,165],"Markov":[27],"decision":[28],"process~(MDP)":[29],"and":[30,113,168,182,201],"determine":[31],"model":[33,172],"parameters":[34],"policy":[36,55,126],"gradient.":[37],"Though":[38],"preliminary":[39],"success":[40],"has":[41],"been":[42],"shown,":[43],"these":[44],"are":[46,133],"still":[47],"far":[48],"from":[49],"achieving":[50],"their":[51],"full":[52],"potentials.":[53],"Existing":[54],"gradient":[56,72,106,127,185],"methods":[57],"directly":[58],"utilize":[59],"absolute":[61],"performance":[62,191],"scores":[63],"(returns)":[64],"sampled":[67,142],"lists":[69,141],"in":[70,109,129,197],"its":[71],"estimations,":[73,107],"which":[74,92,130],"may":[75],"cause":[76],"two":[77,139],"limitations:":[78],"1)":[79],"fail":[80],"reflect":[82],"relative":[84],"goodness":[85],"documents":[87],"within":[88,143],"same":[90,145],"query,":[91],"usually":[93],"is":[94],"close":[95],"nature":[98],"IR":[100],"ranking;":[101],"2)":[102],"generate":[103],"high":[104],"variance":[105,184],"resulting":[108],"slow":[110],"learning":[111],"speed":[112],"low":[114,183],"accuracy.":[116],"To":[117],"deal":[118],"issues,":[121],"we":[122],"propose":[123],"a":[124],"novel":[125],"algorithm":[128],"gradients":[132,164],"determined":[134],"using":[135],"pairwise":[136,166],"comparisons":[137],"query.":[146],"The":[147],"algorithm,":[148],"referred":[149],"as":[151],"Pairwise":[152],"Policy":[153],"Gradient":[154],"(PPG),":[155],"repeatedly":[156],"samples":[157],"pairs":[158],"lists,":[161],"estimates":[162],"comparisons,":[167],"finally":[169],"updates":[170],"parameters.":[173],"Theoretical":[174],"analysis":[175],"shows":[176],"that":[177],"PPG":[178],"makes":[179],"an":[180],"unbiased":[181],"estimations.":[186],"Experimental":[187],"results":[188],"have":[189],"demonstrated":[190],"gains":[192],"over":[193],"state-of-the-art":[195],"baselines":[196],"search":[198],"result":[199],"diversification":[200],"text":[202],"retrieval.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}