{"id":"https://openalex.org/W4383109287","doi":"https://doi.org/10.1109/icra48891.2023.10160374","title":"Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control","display_name":"Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383109287","doi":"https://doi.org/10.1109/icra48891.2023.10160374"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100380049","display_name":"Jiayu Chen","orcid":"https://orcid.org/0000-0002-7708-5247"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayu Chen","raw_affiliation_strings":["School of Industrial Engineering, Purdue University,West Lafayette,IN,USA,47907"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Purdue University,West Lafayette,IN,USA,47907","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tian Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Lan","raw_affiliation_strings":["George Washington University,Department of Electrical and Computer Engineering,Washington D.C.,USA,20052"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University,Department of Electrical and Computer Engineering,Washington D.C.,USA,20052","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064822688","display_name":"Vaneet Aggarwal","orcid":"https://orcid.org/0000-0001-9131-4723"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Vaneet Aggarwal","raw_affiliation_strings":["KAUST,CS Department,Thuwal,Saudi Arabia","CS Department, KAUST, Thuwal, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAUST,CS Department,Thuwal,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"CS Department, KAUST, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9177,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.88136028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5902","last_page":"5908"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9923999905586243,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7627750635147095},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7144821286201477},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6760174036026001},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.66607266664505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6270831823348999},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5703427791595459},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5500730276107788},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5252829790115356},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.432379812002182},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.4315013885498047},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4172239601612091},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.23773834109306335},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.17683729529380798},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11198121309280396},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10144466161727905}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7627750635147095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7144821286201477},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6760174036026001},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.66607266664505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6270831823348999},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5703427791595459},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5500730276107788},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5252829790115356},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.432379812002182},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.4315013885498047},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4172239601612091},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.23773834109306335},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.17683729529380798},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11198121309280396},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10144466161727905},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra48891.2023.10160374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/682325","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/682325","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W592244745","https://openalex.org/W1636244751","https://openalex.org/W1931877416","https://openalex.org/W1959608418","https://openalex.org/W1969074599","https://openalex.org/W1985690171","https://openalex.org/W1986014385","https://openalex.org/W2048305092","https://openalex.org/W2051228319","https://openalex.org/W2057978375","https://openalex.org/W2098774185","https://openalex.org/W2105594594","https://openalex.org/W2109910161","https://openalex.org/W2140911775","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2481567506","https://openalex.org/W2498991332","https://openalex.org/W2736601468","https://openalex.org/W2755546070","https://openalex.org/W2895192407","https://openalex.org/W2902125520","https://openalex.org/W2942034515","https://openalex.org/W2960876848","https://openalex.org/W2963277051","https://openalex.org/W2963508354","https://openalex.org/W2963864421","https://openalex.org/W3091086138","https://openalex.org/W3091776553","https://openalex.org/W3120229615","https://openalex.org/W3167983015","https://openalex.org/W3206298348","https://openalex.org/W4214717370","https://openalex.org/W4288325991","https://openalex.org/W4289145571","https://openalex.org/W4294022794","https://openalex.org/W4295837424","https://openalex.org/W4385245566","https://openalex.org/W6604653223","https://openalex.org/W6617744952","https://openalex.org/W6635487010","https://openalex.org/W6640174482","https://openalex.org/W6640963894","https://openalex.org/W6674884181","https://openalex.org/W6681130209","https://openalex.org/W6684921986","https://openalex.org/W6718092244","https://openalex.org/W6721743441","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6744181227","https://openalex.org/W6745347688","https://openalex.org/W6748972340","https://openalex.org/W6754848371","https://openalex.org/W6756908582","https://openalex.org/W6761754428","https://openalex.org/W6762533131","https://openalex.org/W6763665168","https://openalex.org/W6780559895","https://openalex.org/W6784571263","https://openalex.org/W6787662236","https://openalex.org/W6796441166"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2502115930","https://openalex.org/W2752972570","https://openalex.org/W4297051394","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2976657239"],"abstract_inverted_index":{"Hierarchical":[0],"Imitation":[1],"Learning":[2,67],"(HIL)":[3],"has":[4],"been":[5],"proposed":[6],"to":[7,51,77,94,98,128],"recover":[8,79],"highly-complex":[9],"behaviors":[10],"in":[11,45,75,113],"long-horizon":[12],"tasks":[13,125],"from":[14,83],"expert":[15],"demonstrations":[16],"by":[17],"modeling":[18],"the":[19,23,30,34,43,72,84,95,100,130],"task":[20],"hierarchy":[21],"with":[22,71,110],"option":[24],"framework.":[25],"Existing":[26],"methods":[27],"either":[28],"overlook":[29],"causal":[31],"relationship":[32],"between":[33],"subtask":[35],"and":[36,68,102,119],"its":[37],"corresponding":[38],"policy":[39,44,82],"or":[40],"cannot":[41],"learn":[42],"an":[46,114],"end-to-end":[47,115],"fashion,":[48],"which":[49],"leads":[50],"suboptimality.":[52],"In":[53],"this":[54],"work,":[55],"we":[56,88],"develop":[57],"a":[58,80,90,104],"novel":[59],"HIL":[60],"algorithm":[61,74],"based":[62],"on":[63,121],"Adversarial":[64],"Inverse":[65],"Reinforcement":[66],"adapt":[69],"it":[70],"Expectation-Maximization":[73],"order":[76],"directly":[78],"hierarchical":[81],"unannotated":[85],"demonstrations.":[86],"Further,":[87],"introduce":[89],"directed":[91],"information":[92],"term":[93],"objective":[96],"function":[97],"enhance":[99],"causality":[101],"propose":[103],"Variational":[105],"Autoencoder":[106],"framework":[107],"for":[108],"learning":[109],"our":[111,133],"objectives":[112],"fashion.":[116],"Theoretical":[117],"justifications":[118],"evaluations":[120],"challenging":[122],"robotic":[123],"control":[124],"are":[126,137],"provided":[127],"show":[129],"superiority":[131],"of":[132],"algorithm.":[134],"The":[135],"codes":[136],"available":[138],"at":[139],"https://github.com/LucasCJYSDL/HierAIRL.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}