{"id":"https://openalex.org/W4399939232","doi":"https://doi.org/10.1109/lra.2024.3418275","title":"Aligning Human Intent From Imperfect Demonstrations With Confidence-Based Inverse Soft-Q Learning","display_name":"Aligning Human Intent From Imperfect Demonstrations With Confidence-Based Inverse Soft-Q Learning","publication_year":2024,"publication_date":"2024-06-24","ids":{"openalex":"https://openalex.org/W4399939232","doi":"https://doi.org/10.1109/lra.2024.3418275"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3418275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3418275","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Robotics and Automation Letters","raw_type":"journal-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/A5035956372","display_name":"X. B. Bu","orcid":"https://orcid.org/0009-0004-8132-4599"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xizhou Bu","raw_affiliation_strings":["School of Astronautics, Northwestern Polytechnical University, Xi&#x0027;an, China","School of Astronautics, Northwestern Polytechnical University, Xi'an, Shaanxi 710072 China"],"raw_orcid":"https://orcid.org/0009-0004-8132-4599","affiliations":[{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi'an, Shaanxi 710072 China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757040","display_name":"Wenjuan Li","orcid":"https://orcid.org/0000-0003-3745-5669"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjuan Li","raw_affiliation_strings":["School of Astronautics, Northwestern Polytechnical University, Xi&#x0027;an, China","School of Astronautics, Northwestern Polytechnical University, Xi'an, Shaanxi 710072 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi'an, Shaanxi 710072 China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083493899","display_name":"Zhengxiong Liu","orcid":"https://orcid.org/0000-0002-9427-4066"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengxiong Liu","raw_affiliation_strings":["School of Astronautics, Northwestern Polytechnical University, Xi&#x0027;an, China","School of Astronautics, Northwestern Polytechnical University, Xi'an, Shaanxi 710072 China"],"raw_orcid":"https://orcid.org/0000-0002-9427-4066","affiliations":[{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi'an, Shaanxi 710072 China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028318732","display_name":"Zhiqiang Ma","orcid":"https://orcid.org/0000-0002-6791-1162"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Ma","raw_affiliation_strings":["School of Astronautics, Northwestern Polytechnical University, Xi&#x0027;an, China","School of Astronautics, Northwestern Polytechnical University, Xi'an, Shaanxi 710072 China"],"raw_orcid":"https://orcid.org/0000-0002-6791-1162","affiliations":[{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi'an, Shaanxi 710072 China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091127758","display_name":"Panfeng Huang","orcid":"https://orcid.org/0000-0002-5132-9602"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Panfeng Huang","raw_affiliation_strings":["School of Astronautics, Northwestern Polytechnical University, Xi&#x0027;an, China","School of Astronautics, Northwestern Polytechnical University, Xi'an, Shaanxi 710072 China"],"raw_orcid":"https://orcid.org/0000-0002-5132-9602","affiliations":[{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi'an, Shaanxi 710072 China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035956372"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.9934,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79297028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"9","issue":"8","first_page":"7150","last_page":"7157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7972999811172485,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7972999811172485,"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/T10320","display_name":"Neural Networks and Applications","score":0.696399986743927,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.6448000073432922,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/imperfect","display_name":"Imperfect","score":0.7976299524307251},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5044616460800171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4612279236316681},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.433363139629364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34525614976882935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25937139987945557},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2241484820842743},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.09282007813453674},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07975760102272034},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.077507883310318}],"concepts":[{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.7976299524307251},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5044616460800171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4612279236316681},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.433363139629364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34525614976882935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25937139987945557},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2241484820842743},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.09282007813453674},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07975760102272034},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.077507883310318}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3418275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3418275","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G172774376","display_name":null,"funder_award_id":"62373305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7676250215","display_name":null,"funder_award_id":"62273280","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W2119567691","https://openalex.org/W2174803659","https://openalex.org/W2201912979","https://openalex.org/W2964912293","https://openalex.org/W3002093512","https://openalex.org/W3003310656","https://openalex.org/W3105871743","https://openalex.org/W3144127138","https://openalex.org/W3191453585","https://openalex.org/W4225737910","https://openalex.org/W4287552525","https://openalex.org/W4378474292","https://openalex.org/W4383860829","https://openalex.org/W4388274718","https://openalex.org/W6675944832","https://openalex.org/W6680724558","https://openalex.org/W6718092244","https://openalex.org/W6735677848","https://openalex.org/W6741832191","https://openalex.org/W6747473740","https://openalex.org/W6759312711","https://openalex.org/W6761908843","https://openalex.org/W6766596570","https://openalex.org/W6767611730","https://openalex.org/W6769174716","https://openalex.org/W6784678651","https://openalex.org/W6785034342","https://openalex.org/W6786981901","https://openalex.org/W6796947852","https://openalex.org/W6797805595","https://openalex.org/W6799150178","https://openalex.org/W6802868314","https://openalex.org/W6810476337","https://openalex.org/W6840198410","https://openalex.org/W6846930601","https://openalex.org/W6853337198","https://openalex.org/W6853830055","https://openalex.org/W6858202927"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2374250903","https://openalex.org/W1546413948","https://openalex.org/W2263832889","https://openalex.org/W2243884323","https://openalex.org/W42072456","https://openalex.org/W2390279801","https://openalex.org/W4243095785","https://openalex.org/W2358668433"],"abstract_inverted_index":{"Imitation":[0],"learning":[1,130],"attracts":[2],"much":[3],"attention":[4],"for":[5,101,132],"its":[6],"ability":[7,51],"to":[8,11,48,52,69,80,96],"allow":[9],"robots":[10,46],"quickly":[12],"learn":[13,53],"human":[14,24,38,59,86,169],"manipulation":[15],"skills":[16],"through":[17],"demonstrations.":[18,63],"However,":[19],"in":[20,144],"the":[21,50,104,110,114],"real":[22],"world,":[23],"demonstrations":[25],"often":[26],"exhibit":[27],"random":[28],"behavior":[29],"that":[30,56,163],"is":[31,40,165],"not":[32],"intended":[33],"by":[34,117],"humans.":[35],"Collecting":[36],"high-quality":[37],"datasets":[39],"both":[41],"challenging":[42],"and":[43,161],"expensive.":[44],"Consequently,":[45],"need":[47],"have":[49],"behavioral":[54],"policies":[55],"align":[57],"with":[58,168],"intent":[60,170],"from":[61,73],"imperfect":[62,74],"Previous":[64],"work":[65],"uses":[66],"confidence":[67,99],"scores":[68,100],"extract":[70],"useful":[71],"information":[72],"demonstrations,":[75],"which":[76,107],"relies":[77],"on":[78,122,152],"access":[79],"ground":[81],"truth":[82],"rewards":[83],"or":[84],"active":[85],"supervision.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91,154],"propose":[92],"a":[93,126],"transition-based":[94],"method":[95],"obtain":[97],"fine-grained":[98],"data":[102],"without":[103],"above":[105],"efforts,":[106],"can":[108],"increase":[109],"success":[111],"rate":[112],"of":[113,158],"baseline":[115],"algorithm":[116],"40.3<inline-formula":[118],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[119,149,173],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[120],"notation=\"LaTeX\">$\\%$</tex-math></inline-formula>":[121],"average.":[123],"We":[124],"develop":[125],"generalized":[127],"confidence-based":[128],"imitation":[129],"framework":[131],"guiding":[133],"policy":[134],"learning,":[135],"called":[136],"Confidence-based":[137],"Inverse":[138],"soft-Q":[139],"Learning":[140],"(CIQL),":[141],"as":[142],"shown":[143],"Fig.":[145],"<xref":[146],"ref-type=\"fig\"":[147],"rid=\"fig1\"":[148],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</xref>.":[150],"Based":[151],"this,":[153],"analyze":[155],"two":[156],"ways":[157],"processing":[159],"noise":[160],"find":[162],"penalization":[164],"more":[166],"aligned":[167],"than":[171],"filtering.<sup":[172],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
