{"id":"https://openalex.org/W4221160489","doi":"https://doi.org/10.1007/s10791-022-09413-y","title":"Reinforcement online learning to rank with unbiased reward shaping","display_name":"Reinforcement online learning to rank with unbiased reward shaping","publication_year":2022,"publication_date":"2022-08-04","ids":{"openalex":"https://openalex.org/W4221160489","doi":"https://doi.org/10.1007/s10791-022-09413-y"},"language":"en","primary_location":{"id":"doi:10.1007/s10791-022-09413-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-022-09413-y","pdf_url":null,"source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s10791-022-09413-y","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012958162","display_name":"Shengyao Zhuang","orcid":"https://orcid.org/0000-0002-6711-0955"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Shengyao Zhuang","raw_affiliation_strings":["The University of Queensland, St Lucia, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland, St Lucia, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016112845","display_name":"Zhihao Qiao","orcid":"https://orcid.org/0000-0002-7822-5846"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhihao Qiao","raw_affiliation_strings":["The University of Queensland, St Lucia, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland, St Lucia, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076031002","display_name":"Guido Zuccon","orcid":"https://orcid.org/0000-0003-0271-5563"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guido Zuccon","raw_affiliation_strings":["The University of Queensland, St Lucia, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0271-5563","affiliations":[{"raw_affiliation_string":"The University of Queensland, St Lucia, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012958162"],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":0.8751,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79677693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"25","issue":"4","first_page":"386","last_page":"413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9970999956130981,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965000152587891,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9926000237464905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.794879674911499},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7402366995811462},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.7400683164596558},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7009463906288147},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5773410797119141},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5434846878051758},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5260595679283142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4637981057167053},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4315851330757141},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4183487892150879},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41779494285583496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07282355427742004}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794879674911499},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7402366995811462},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.7400683164596558},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7009463906288147},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5773410797119141},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5434846878051758},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5260595679283142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4637981057167053},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4315851330757141},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4183487892150879},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41779494285583496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07282355427742004},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10791-022-09413-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-022-09413-y","pdf_url":null,"source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval Journal","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10791-022-09413-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-022-09413-y","pdf_url":null,"source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval Journal","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320984","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W1963548721","https://openalex.org/W2007815473","https://openalex.org/W2009979684","https://openalex.org/W2022995284","https://openalex.org/W2047221353","https://openalex.org/W2048437343","https://openalex.org/W2102217663","https://openalex.org/W2102693936","https://openalex.org/W2112430581","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2147892741","https://openalex.org/W2149427297","https://openalex.org/W2155027007","https://openalex.org/W2156541733","https://openalex.org/W2176930994","https://openalex.org/W2279385734","https://openalex.org/W2340526403","https://openalex.org/W2464171116","https://openalex.org/W2505872937","https://openalex.org/W2507134384","https://openalex.org/W2566147423","https://openalex.org/W2604520541","https://openalex.org/W2610395436","https://openalex.org/W2739916191","https://openalex.org/W2740384884","https://openalex.org/W2740935584","https://openalex.org/W2769473018","https://openalex.org/W2788295351","https://openalex.org/W2797400361","https://openalex.org/W2798634418","https://openalex.org/W2798694866","https://openalex.org/W2799043514","https://openalex.org/W2799544270","https://openalex.org/W2889658777","https://openalex.org/W2890291106","https://openalex.org/W2899259597","https://openalex.org/W2905569957","https://openalex.org/W2912255075","https://openalex.org/W2913544988","https://openalex.org/W2948795993","https://openalex.org/W3012600133","https://openalex.org/W3012886296","https://openalex.org/W3015271280","https://openalex.org/W3022971154","https://openalex.org/W3026200234","https://openalex.org/W3028135017","https://openalex.org/W3028556448","https://openalex.org/W3035106673","https://openalex.org/W3044556022","https://openalex.org/W3048156405","https://openalex.org/W3099096815","https://openalex.org/W3099404779","https://openalex.org/W3101148092","https://openalex.org/W3101267375","https://openalex.org/W3101935024","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3103733168","https://openalex.org/W3104474754","https://openalex.org/W3105712174","https://openalex.org/W3112511105","https://openalex.org/W3115087172","https://openalex.org/W3130740428","https://openalex.org/W3135277963","https://openalex.org/W3145282602","https://openalex.org/W3156096500","https://openalex.org/W3157410348","https://openalex.org/W3197288708","https://openalex.org/W4251188927","https://openalex.org/W4288280739","https://openalex.org/W4302313152","https://openalex.org/W6677916085","https://openalex.org/W6682735415","https://openalex.org/W6747597888"],"related_works":["https://openalex.org/W3127142483","https://openalex.org/W3160516639","https://openalex.org/W4385565564","https://openalex.org/W2898073868","https://openalex.org/W2138488530","https://openalex.org/W4390446658","https://openalex.org/W2971071571","https://openalex.org/W2798835721","https://openalex.org/W2922169395","https://openalex.org/W2387658907"],"abstract_inverted_index":{"Abstract":[0],"Online":[1,63],"learning":[2,51,58],"to":[3,7,33,59,65,82,89,137],"rank":[4],"(OLTR)":[5],"aims":[6],"learn":[8],"a":[9,25,49,127,140],"ranker":[10,74],"directly":[11],"from":[12,16],"implicit":[13],"feedback":[14],"derived":[15],"users\u2019":[17,92],"interactions,":[18],"such":[19],"as":[20],"clicks.":[21],"Clicks":[22],"however":[23],"are":[24,31,75,135],"biased":[26],"signal:":[27],"specifically,":[28],"top-ranked":[29],"documents":[30,38,125],"likely":[32],"attract":[34],"more":[35],"clicks":[36],"than":[37,165],"down":[39],"the":[40,70,73,79,91,97,171],"ranking":[41],"(position":[42],"bias).":[43],"In":[44,68,87],"this":[45],"paper,":[46],"we":[47,100,176],"propose":[48],"novel":[50],"algorithm":[52],"for":[53,111],"OLTR":[54,151,167],"that":[55,106,118,131,154],"uses":[56],"reinforcement":[57],"optimize":[60],"rankers:":[61],"Reinforcement":[62],"Learning":[64],"Rank":[66],"(ROLTR).":[67],"ROLTR,":[69],"gradients":[71],"of":[72,173],"estimated":[76],"based":[77],"on":[78,149],"rewards":[80],"assigned":[81],"clicked":[83,112],"and":[84,113,159],"unclicked":[85,114,124],"documents.":[86,115],"order":[88],"de-bias":[90],"position":[93],"bias":[94],"contained":[95],"in":[96,130,145],"reward":[98,103],"signals,":[99],"introduce":[101],"unbiased":[102],"shaping":[104],"functions":[105],"exploit":[107],"inverse":[108],"propensity":[109],"scoring":[110],"The":[116],"fact":[117],"our":[119,174],"method":[120],"can":[121],"also":[122],"model":[123],"provides":[126,160],"further":[128],"advantage":[129],"less":[132],"users":[133],"interactions":[134],"required":[136],"effectively":[138],"train":[139],"ranker,":[141],"thus":[142],"providing":[143],"gains":[144],"efficiency.":[146],"Empirical":[147],"evaluation":[148],"standard":[150],"datasets":[152],"shows":[153],"ROLTR":[155],"achieves":[156],"state-of-the-art":[157],"performance,":[158],"significantly":[161],"better":[162],"user":[163],"experience":[164],"other":[166],"approaches.":[168],"To":[169],"facilitate":[170],"reproducibility":[172],"experiments,":[175],"make":[177],"all":[178],"experiment":[179],"code":[180],"available":[181],"at":[182],"https://github.com/ielab/OLTR":[183],".":[184]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}