{"id":"https://openalex.org/W4386702747","doi":"https://doi.org/10.1109/tnnls.2023.3305983","title":"Hierarchical Adversarial Inverse Reinforcement Learning","display_name":"Hierarchical Adversarial Inverse Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-13","ids":{"openalex":"https://openalex.org/W4386702747","doi":"https://doi.org/10.1109/tnnls.2023.3305983","pmid":"https://pubmed.ncbi.nlm.nih.gov/37703157"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3305983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3305983","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","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":"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"],"raw_orcid":"https://orcid.org/0000-0002-7708-5247","affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018464968","display_name":"Tian Lan","orcid":"https://orcid.org/0000-0003-3010-8090"},"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":["Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0000-0003-3010-8090","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA","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/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Vaneet Aggarwal","raw_affiliation_strings":["School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","Computer Science Department, KAUST, Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-9131-4723","affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Computer Science 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":1.3185,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83935873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"35","issue":"12","first_page":"17549","last_page":"17558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9932000041007996,"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":0.9932000041007996,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.957099974155426,"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":0.9474999904632568,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7728325128555298},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7042602300643921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6840956807136536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5865048170089722},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5021164417266846},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49857521057128906},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.475184828042984},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4600076973438263},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13628339767456055}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7728325128555298},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7042602300643921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840956807136536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5865048170089722},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5021164417266846},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49857521057128906},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.475184828042984},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4600076973438263},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13628339767456055},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3305983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3305983","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37703157","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37703157","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 neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4568529184","display_name":null,"funder_award_id":"N00014-23-1-2532","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1636244751","https://openalex.org/W1985690171","https://openalex.org/W1986014385","https://openalex.org/W2048305092","https://openalex.org/W2051228319","https://openalex.org/W2109910161","https://openalex.org/W2158782408","https://openalex.org/W2347074400","https://openalex.org/W2498991332","https://openalex.org/W2791797404","https://openalex.org/W2952298682","https://openalex.org/W2962845991","https://openalex.org/W2964227312","https://openalex.org/W2966477753","https://openalex.org/W2968301466","https://openalex.org/W3091086138","https://openalex.org/W3134110625","https://openalex.org/W3174733757","https://openalex.org/W3200276130","https://openalex.org/W3203504876","https://openalex.org/W3206298348","https://openalex.org/W4284965199","https://openalex.org/W4307234290","https://openalex.org/W4385245566","https://openalex.org/W6617744952","https://openalex.org/W6635487010","https://openalex.org/W6640174482","https://openalex.org/W6640443443","https://openalex.org/W6674884181","https://openalex.org/W6677555207","https://openalex.org/W6681130209","https://openalex.org/W6684921986","https://openalex.org/W6718092244","https://openalex.org/W6741002519","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/W6778961322","https://openalex.org/W6780559895","https://openalex.org/W6784571263","https://openalex.org/W6787662236","https://openalex.org/W6796441166","https://openalex.org/W6809882875","https://openalex.org/W6852842027","https://openalex.org/W6855195674"],"related_works":["https://openalex.org/W3013360982","https://openalex.org/W4287598984","https://openalex.org/W3145910327","https://openalex.org/W3101326751","https://openalex.org/W4386212471","https://openalex.org/W3074294383","https://openalex.org/W2964108292","https://openalex.org/W2891191051","https://openalex.org/W3046843850","https://openalex.org/W4319083788"],"abstract_inverted_index":{"Imitation":[0],"learning":[1,113],"(IL)":[2],"has":[3,42],"been":[4,43],"proposed":[5],"to":[6,18,45,84,99,147,151,179,207],"recover":[7],"the":[8,31,56,63,71,75,79,86,92,123,130,134,148,153,156,183,209],"expert":[9,32,51,180],"policy":[10,23,33,49,90,158],"from":[11,50],"demonstrations.":[12],"However,":[13],"it":[14,175],"would":[15],"be":[16,177],"difficult":[17],"learn":[19,46,85],"a":[20,47,60,106,117,143],"single":[21],"monolithic":[22],"for":[24],"highly":[25],"complex":[26],"long-horizon":[27],"tasks":[28,204],"of":[29,170,194,211],"which":[30,97,115,186],"usually":[34],"contains":[35],"subtask":[36,76,184],"hierarchies.":[37],"Therefore,":[38],"hierarchical":[39,48,93],"IL":[40,120],"(HIL)":[41],"developed":[44],"demonstrations":[52,181],"through":[53],"explicitly":[54],"modeling":[55],"activity":[57],"structure":[58,77],"in":[59,91,95,190],"task":[61],"with":[62,122,215],"option":[64,125],"framework.":[65,126],"Existing":[66],"HIL":[67,108,217],"methods":[68],"either":[69],"overlook":[70],"causal":[72],"relationship":[73],"between":[74,155],"and":[78,88,137,140,159,198],"learned":[80],"policy,":[81],"or":[82],"fail":[83],"high-level":[87],"low-level":[89,157],"framework":[94],"conjuncture,":[96],"leads":[98],"suboptimality.":[100],"In":[101],"this":[102],"work,":[103],"we":[104,128,164],"propose":[105,165],"novel":[107],"algorithm-hierarchical":[109],"adversarial":[110],"inverse":[111],"reinforcement":[112],"(H-AIRL),":[114],"extends":[116],"state-of-the-art":[118],"(SOTA)":[119],"algorithm-AIRL,":[121],"one-step":[124],"Specifically,":[127],"redefine":[129],"AIRL":[131],"objectives":[132],"on":[133,200],"extended":[135],"state":[136],"action":[138],"spaces,":[139],"further":[141],"introduce":[142],"directed":[144],"information":[145],"term":[146],"objective":[149],"function":[150],"enhance":[152],"causality":[154],"its":[160],"corresponding":[161],"subtask.":[162],"Moreover,":[163],"an":[166],"expectation-maximization":[167],"(EM)":[168],"adaption":[169],"our":[171,195,212],"algorithm":[172,196,213],"so":[173],"that":[174],"can":[176],"applied":[178],"without":[182],"annotations":[185],"are":[187,205,221],"more":[188],"accessible":[189],"practice.":[191],"Theoretical":[192],"justifications":[193],"design":[197],"evaluations":[199],"challenging":[201],"robotic":[202],"control":[203],"provided":[206],"show":[208],"superiority":[210],"compared":[214],"SOTA":[216],"baselines.":[218],"The":[219],"codes":[220],"available":[222],"at":[223],"https://github.com/LucasCJYSDL/HierAIRL.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}