{"id":"https://openalex.org/W7118159755","doi":"https://doi.org/10.1109/tpami.2026.3650796","title":"IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution History","display_name":"IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution History","publication_year":2026,"publication_date":"2026-01-05","ids":{"openalex":"https://openalex.org/W7118159755","doi":"https://doi.org/10.1109/tpami.2026.3650796","pmid":"https://pubmed.ncbi.nlm.nih.gov/41489964"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3650796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3650796","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yi Xu","orcid":"https://orcid.org/0009-0004-2076-5374"},"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":"Yi Xu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2076-5374","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059901703","display_name":"Weiran Shen","orcid":"https://orcid.org/0000-0003-4366-9276"},"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":"Weiran Shen","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4366-9276","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":null,"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":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7170-111X","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121952492","display_name":"Xiao Zhang","orcid":null},"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":"Xiao Zhang","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7397-5632","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084170249","display_name":"Ji\u2013Rong Wen","orcid":null},"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":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9777-9676","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02012777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"5","first_page":"5655","last_page":"5671"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.8748000264167786,"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":0.8748000264167786,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.03620000183582306,"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":0.019500000402331352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6212999820709229},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5752000212669373},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.3549000024795532},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.3483000099658966},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.34130001068115234},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.33809998631477356},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.33799999952316284},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.33649998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383999824523926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6402999758720398},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6212999820709229},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5756000280380249},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5752000212669373},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.3549000024795532},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33799999952316284},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C51620047","wikidata":"https://www.wikidata.org/wiki/Q23399","display_name":"Memetics","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C78639753","wikidata":"https://www.wikidata.org/wiki/Q3318160","display_name":"Behavioral modeling","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3650796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3650796","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41489964","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41489964","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.76016765832901,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1840373507","display_name":null,"funder_award_id":"62376275","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5643227726","display_name":null,"funder_award_id":"62472426","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1596877211","https://openalex.org/W1999874108","https://openalex.org/W2013439434","https://openalex.org/W2031571562","https://openalex.org/W2054141820","https://openalex.org/W2056716515","https://openalex.org/W2080514141","https://openalex.org/W2112420033","https://openalex.org/W2129516068","https://openalex.org/W2134491302","https://openalex.org/W2145339207","https://openalex.org/W2150713082","https://openalex.org/W2174803659","https://openalex.org/W2494566063","https://openalex.org/W2601943843","https://openalex.org/W2604382266","https://openalex.org/W2769646558","https://openalex.org/W2904688694","https://openalex.org/W2997591727","https://openalex.org/W3038664881","https://openalex.org/W3130906801","https://openalex.org/W3138984732","https://openalex.org/W3155850838","https://openalex.org/W3208231292","https://openalex.org/W4290927796","https://openalex.org/W4307234290","https://openalex.org/W4360584316","https://openalex.org/W4387773565"],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"imitation":[1,71,174,195],"learning":[2,40,72,175,207],"focuses":[3],"on":[4,109,177],"modeling":[5],"the":[6,42,47,110,118,129,134,208,212],"behavioral":[7,56,112,130],"mechanisms":[8],"of":[9,16,101,133,215],"experts,":[10,199],"which":[11],"requires":[12],"a":[13,66,122,155],"large":[14],"amount":[15],"interaction":[17,48,213],"history":[18,49,132,214],"generated":[19,50],"by":[20,51,127],"some":[21],"fixed":[22],"expert.":[23,63],"However,":[24],"in":[25,38,206],"many":[26],"streaming":[27,31],"applications,":[28],"such":[29],"as":[30],"recommender":[32],"systems,":[33],"online":[34,39,52],"decision-makers":[35,53],"typically":[36],"engage":[37],"during":[41],"decision-making":[43],"process,":[44],"meaning":[45],"that":[46,74,96,152,169,191],"includes":[54],"their":[55],"evolution":[57,113,131],"from":[58,79,211],"novice":[59,216],"expert":[60,148],"to":[61,146],"experienced":[62,80],"This":[64],"poses":[65],"new":[67],"challenge":[68],"for":[69,158,197],"existing":[70,173],"approaches":[73],"can":[75,97,143],"only":[76],"utilize":[77],"data":[78,181],"experts.":[81,217],"To":[82],"address":[83],"this":[84,86],"issue,":[85],"paper":[87],"proposes":[88],"an":[89],"inverse":[90,119],"batched":[91,135],"contextual":[92,136],"bandit":[93,137,163,209],"(IBCB)":[94],"framework":[95,157],"efficiently":[98],"perform":[99],"estimations":[100],"environment":[102],"reward":[103],"parameters":[104],"and":[105,141,161,179,182,202],"learned":[106],"policy":[107,210],"based":[108],"expert's":[111],"history.":[114],"Specifically,":[115],"IBCB":[116,153,170,192],"formulates":[117],"problem":[120,126],"into":[121],"simple":[123],"quadratic":[124],"programming":[125],"utilizing":[128],"with":[138],"inaccessible":[139],"rewards,":[140],"it":[142],"be":[144],"extended":[145],"fairness-aware":[147,198],"limitation.":[149],"We":[150],"demonstrate":[151],"is":[154,203,220],"unified":[156],"both":[159],"deterministic":[160],"randomized":[162],"policies.":[164],"The":[165,218],"experimental":[166],"results":[167],"indicate":[168],"outperforms":[171],"several":[172],"algorithms":[176],"synthetic":[178],"real-world":[180],"significantly":[183],"reduces":[184],"running":[185],"time.":[186],"Additionally,":[187],"empirical":[188],"analyses":[189],"reveal":[190],"exhibits":[193],"better":[194],"ability":[196],"out-of-distribution":[200],"generalization":[201],"highly":[204],"effective":[205],"code":[219],"publicly":[221],"available.":[222]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-01-05T00:00:00"}