{"id":"https://openalex.org/W4372349498","doi":"https://doi.org/10.1109/icassp49357.2023.10096692","title":"Learning Unbiased Rewards with Mutual Information in Adversarial Imitation Learning","display_name":"Learning Unbiased Rewards with Mutual Information in Adversarial Imitation Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349498","doi":"https://doi.org/10.1109/icassp49357.2023.10096692"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096692","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100414890","display_name":"Lihua Zhang","orcid":"https://orcid.org/0000-0001-5770-9529"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lihua Zhang","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,China","School of Computer Science and Technology, Soochow University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414574","display_name":"Quan Liu","orcid":"https://orcid.org/0000-0002-8710-1810"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Liu","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,China","School of Computer Science and Technology, Soochow University, Suzhou, China","Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086179182","display_name":"Zhigang Huang","orcid":"https://orcid.org/0000-0003-1959-2192"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Huang","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,China","School of Computer Science and Technology, Soochow University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108030925","display_name":"Lan Wu","orcid":"https://orcid.org/0000-0003-0892-6601"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan Wu","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,China","School of Computer Science and Technology, Soochow University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100414890"],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":0.3921,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62944043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9991000294685364,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9991000294685364,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9986000061035156,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9872000217437744,"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/discriminator","display_name":"Discriminator","score":0.9626611471176147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.732263445854187},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.694489061832428},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5860188007354736},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.569583535194397},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.561852753162384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.560539960861206},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4918365478515625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4389181137084961},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.17068085074424744},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13254502415657043}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9626611471176147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732263445854187},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.694489061832428},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5860188007354736},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.569583535194397},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.561852753162384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.560539960861206},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4918365478515625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4389181137084961},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.17068085074424744},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13254502415657043},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096692","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2604292070","https://openalex.org/W2892806280","https://openalex.org/W2913756371","https://openalex.org/W2988072049","https://openalex.org/W3000681444","https://openalex.org/W3015205859","https://openalex.org/W3191808899","https://openalex.org/W4221150133","https://openalex.org/W4232613155","https://openalex.org/W6680724558","https://openalex.org/W6718092244","https://openalex.org/W6745347688","https://openalex.org/W6747473740","https://openalex.org/W6754484421","https://openalex.org/W6776175605","https://openalex.org/W6779381009","https://openalex.org/W6785260215","https://openalex.org/W6796190733","https://openalex.org/W6797377937","https://openalex.org/W6803297132","https://openalex.org/W6803936620"],"related_works":["https://openalex.org/W2995777218","https://openalex.org/W4293320219","https://openalex.org/W2953246223","https://openalex.org/W4283584549","https://openalex.org/W2554314924","https://openalex.org/W4288256692","https://openalex.org/W2998859928","https://openalex.org/W4381885966","https://openalex.org/W2969399009","https://openalex.org/W4398186750"],"abstract_inverted_index":{"A":[0],"powerful":[1],"method":[2],"for":[3],"automated":[4],"decision":[5],"systems":[6],"is":[7,13,62,93,121],"Adversarial":[8],"Imitation":[9],"Learning":[10],"(AIL).":[11],"It":[12],"based":[14,109],"on":[15,114],"a":[16,23,27,35,49,52,88,91,106],"generative":[17],"adversarial":[18],"framework":[19],"that":[20,57,83,119],"alternately":[21],"optimizes":[22],"generator":[24,50,89],"(learner)":[25],"and":[26,51,64,81,90,133,138],"discriminator":[28,37,92],"(reward":[29],"function).":[30],"In":[31],"the":[32,46,58,74,77,85,125,129],"popular":[33],"mind,":[34],"high-accuracy":[36],"results":[38,66],"in":[39,67,76],"informative":[40,68],"rewards,":[41],"thus":[42],"AIL":[43,59,78,130],"must":[44],"balance":[45],"performance":[47,86],"between":[48],"discriminator.":[53],"However,":[54],"we":[55,71,97,104],"find":[56,82],"reward":[60,79,101,111,131],"function":[61,80,132],"biased":[63],"also":[65],"rewards.":[69],"Thus,":[70],"theoretically":[72],"analyze":[73],"bias":[75,126],"balancing":[84],"of":[87,128],"not":[94],"necessary":[95],"when":[96],"recover":[98],"an":[99],"unbiased":[100],"function.":[102,112],"Further,":[103],"propose":[105],"mutual":[107],"information":[108],"auxiliary":[110],"Experiments":[113],"continuous":[115],"control":[116],"tasks":[117],"indicate":[118],"MI-GAIL":[120],"able":[122],"to":[123],"address":[124],"problem":[127],"further":[134],"improve":[135],"sample":[136],"efficiency":[137],"training":[139],"stability":[140],"compared":[141],"with":[142],"up-to-date":[143],"algorithms.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}