{"id":"https://openalex.org/W4389665749","doi":"https://doi.org/10.1109/iros55552.2023.10341411","title":"Model-based Adversarial Imitation Learning from Demonstrations and Human Reward","display_name":"Model-based Adversarial Imitation Learning from Demonstrations and Human Reward","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665749","doi":"https://doi.org/10.1109/iros55552.2023.10341411"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5048299480","display_name":"Jie Huang","orcid":"https://orcid.org/0000-0003-1570-6797"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Huang","raw_affiliation_strings":["College of Information Science and Engineering, Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019108944","display_name":"Jiangshan Hao","orcid":"https://orcid.org/0000-0002-5795-0264"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangshan Hao","raw_affiliation_strings":["College of Information Science and Engineering, Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065250586","display_name":"Rongshun Juan","orcid":"https://orcid.org/0000-0002-0840-2528"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongshun Juan","raw_affiliation_strings":["College of Information Science and Engineering, Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Randy Gomez","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd,Wako,Japan","Honda Research Institute Japan Co., Ltd, Wako, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd,Wako,Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd, Wako, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093479827","display_name":"Keisuke Nakarnura","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Nakarnura","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd,Wako,Japan","Honda Research Institute Japan Co., Ltd, Wako, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd,Wako,Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd, Wako, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101812014","display_name":"Guangliang Li","orcid":"https://orcid.org/0000-0003-1728-5711"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangliang Li","raw_affiliation_strings":["College of Information Science and Engineering, Ocean University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ocean University of China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1683","last_page":"1690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9897000193595886,"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":0.9781000018119812,"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/computer-science","display_name":"Computer science","score":0.7833300828933716},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7749114036560059},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7600302696228027},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6648895144462585},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6595698595046997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.656571626663208},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.604710578918457},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5895806550979614},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.541498601436615},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4622570872306824},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4497053325176239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833300828933716},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7749114036560059},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7600302696228027},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6648895144462585},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6595698595046997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.656571626663208},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.604710578918457},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5895806550979614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.541498601436615},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4622570872306824},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4497053325176239},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8754186815","display_name":null,"funder_award_id":"51809246","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1525280637","https://openalex.org/W1977655452","https://openalex.org/W1980035368","https://openalex.org/W2074056782","https://openalex.org/W2121110499","https://openalex.org/W2127572219","https://openalex.org/W2145339207","https://openalex.org/W2156869222","https://openalex.org/W2157331557","https://openalex.org/W2158796564","https://openalex.org/W2295575486","https://openalex.org/W2604738573","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2785389871","https://openalex.org/W2789824229","https://openalex.org/W2884247313","https://openalex.org/W2892806280","https://openalex.org/W2900406861","https://openalex.org/W2944766483","https://openalex.org/W2953708620","https://openalex.org/W2962872206","https://openalex.org/W2963277051","https://openalex.org/W2963411833","https://openalex.org/W2963489214","https://openalex.org/W2990747716","https://openalex.org/W3020718655","https://openalex.org/W3086412568","https://openalex.org/W3090897645","https://openalex.org/W3106764401","https://openalex.org/W3127031155","https://openalex.org/W3136025385","https://openalex.org/W3137837033","https://openalex.org/W3155878512","https://openalex.org/W3174428490","https://openalex.org/W4214717370","https://openalex.org/W4232512588","https://openalex.org/W4288593469","https://openalex.org/W6638018090","https://openalex.org/W6680724558","https://openalex.org/W6682968728","https://openalex.org/W6713055699","https://openalex.org/W6718092244","https://openalex.org/W6732249622","https://openalex.org/W6732417791","https://openalex.org/W6736368053","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6741115023","https://openalex.org/W6741832191","https://openalex.org/W6746581380","https://openalex.org/W6748519856","https://openalex.org/W6748817170","https://openalex.org/W6753770476","https://openalex.org/W6758427599","https://openalex.org/W6764980988","https://openalex.org/W6780559895","https://openalex.org/W6783068448","https://openalex.org/W6791554432","https://openalex.org/W6794780583","https://openalex.org/W6797659266"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,41,48,88],"(RL)":[2],"can":[3,130],"potentially":[4],"be":[5],"applied":[6],"to":[7,23,52,78,139],"real-world":[8],"robot":[9],"control":[10,121],"in":[11,59,70,115],"complex":[12],"and":[13,35,61,91,108,119,136],"uncertain":[14],"environments.":[15,37,63],"However,":[16,64],"it":[17],"is":[18,66],"difficult":[19],"or":[20],"even":[21],"unpractical":[22],"design":[24],"an":[25],"efficient":[26],"reward":[27,93],"function":[28],"for":[29,123],"various":[30],"tasks,":[31],"especially":[32],"those":[33],"large":[34,60],"high-dimensional":[36,62],"Generative":[38],"adversarial":[39,86],"imitation":[40,47,87,99],"(GAIL)":[42],"-":[43],"a":[44,84,95],"general":[45],"model-free":[46],"method,":[49],"allows":[50],"robots":[51],"directly":[53],"learn":[54],"policies":[55],"from":[56,89],"expert":[57],"trajectories":[58],"GAIL":[65],"still":[67],"sample":[68,134],"inefficient":[69],"terms":[71],"of":[72,104],"environmental":[73],"interaction.":[74],"In":[75],"this":[76,80],"paper,":[77],"solve":[79],"problem,":[81],"we":[82],"propose":[83],"model-based":[85,97,109],"demonstrations":[90],"human":[92],"(MAILDH),":[94],"novel":[96],"interactive":[98,106],"framework":[100],"combining":[101],"the":[102,133,140],"advantages":[103],"GAIL,":[105],"RL":[107],"RL.":[110,124],"We":[111],"tested":[112],"our":[113],"method":[114],"eight":[116],"physics-based":[117],"discrete":[118],"continuous":[120],"tasks":[122],"Our":[125],"results":[126],"show":[127],"that":[128],"MAILDH":[129],"greatly":[131],"improve":[132],"efficiency":[135],"robustness":[137],"compared":[138],"original":[141],"GAIL.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}