{"id":"https://openalex.org/W3155878512","doi":"https://doi.org/10.1109/icra48891.2023.10160939","title":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","display_name":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W3155878512","doi":"https://doi.org/10.1109/icra48891.2023.10160939","mag":"3155878512"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160939","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.06600","any_repository_has_fulltext":true},"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/A5049329632","display_name":"Keisuke Nakamura","orcid":"https://orcid.org/0000-0002-4979-2083"},"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 Nakamura","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":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4991","last_page":"4998"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9851999878883362,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9714000225067139,"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":0.8252861499786377},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7140432596206665},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6647218465805054},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6042903661727905},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.5978401899337769},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5166085362434387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47165384888648987},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4559202790260315},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4290265738964081},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41739532351493835},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4136725962162018},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40869200229644775},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10191455483436584}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8252861499786377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7140432596206665},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6647218465805054},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6042903661727905},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.5978401899337769},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5166085362434387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47165384888648987},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4559202790260315},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4290265738964081},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41739532351493835},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4136725962162018},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40869200229644775},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10191455483436584},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra48891.2023.10160939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160939","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:arXiv.org:2104.06600","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.06600","pdf_url":"https://arxiv.org/pdf/2104.06600","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2104.06600","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.06600","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.06600","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.06600","pdf_url":"https://arxiv.org/pdf/2104.06600","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"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":100,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1777239053","https://openalex.org/W1975463331","https://openalex.org/W1977655452","https://openalex.org/W1999874108","https://openalex.org/W2032558547","https://openalex.org/W2061562262","https://openalex.org/W2070469928","https://openalex.org/W2074056782","https://openalex.org/W2098774185","https://openalex.org/W2099471712","https://openalex.org/W2102847492","https://openalex.org/W2113023245","https://openalex.org/W2121110499","https://openalex.org/W2121863487","https://openalex.org/W2142641780","https://openalex.org/W2145339207","https://openalex.org/W2156869222","https://openalex.org/W2158782408","https://openalex.org/W2295575486","https://openalex.org/W2339027962","https://openalex.org/W2591957724","https://openalex.org/W2604738573","https://openalex.org/W2606433045","https://openalex.org/W2726187156","https://openalex.org/W2735089625","https://openalex.org/W2766447205","https://openalex.org/W2785379783","https://openalex.org/W2787938642","https://openalex.org/W2788781499","https://openalex.org/W2788862220","https://openalex.org/W2796290181","https://openalex.org/W2884247313","https://openalex.org/W2892806280","https://openalex.org/W2900406861","https://openalex.org/W2911719076","https://openalex.org/W2933570795","https://openalex.org/W2944766483","https://openalex.org/W2949608212","https://openalex.org/W2962779270","https://openalex.org/W2962872206","https://openalex.org/W2963014947","https://openalex.org/W2963277051","https://openalex.org/W2963286043","https://openalex.org/W2963363446","https://openalex.org/W2963376229","https://openalex.org/W2963411833","https://openalex.org/W2963489214","https://openalex.org/W2963923407","https://openalex.org/W2964118020","https://openalex.org/W2964201867","https://openalex.org/W2964209830","https://openalex.org/W2990747716","https://openalex.org/W2994972935","https://openalex.org/W2998396902","https://openalex.org/W3037533353","https://openalex.org/W3037625705","https://openalex.org/W3040259477","https://openalex.org/W3083131369","https://openalex.org/W3104515094","https://openalex.org/W3111359613","https://openalex.org/W3188220908","https://openalex.org/W3197594072","https://openalex.org/W3208134787","https://openalex.org/W4211089519","https://openalex.org/W4213440380","https://openalex.org/W4214717370","https://openalex.org/W4232512588","https://openalex.org/W4288347236","https://openalex.org/W4288593469","https://openalex.org/W4289288058","https://openalex.org/W4298857966","https://openalex.org/W4300110528","https://openalex.org/W4312828991","https://openalex.org/W4320013936","https://openalex.org/W4394666657","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6638088447","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6680724558","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/W6741115023","https://openalex.org/W6748314335","https://openalex.org/W6748523217","https://openalex.org/W6748839928","https://openalex.org/W6753960536","https://openalex.org/W6758427599","https://openalex.org/W6759312711","https://openalex.org/W6768425981","https://openalex.org/W6772300770","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Generative":[0],"adversarial":[1],"imitation":[2,9,31],"learning":[3,10,32,57],"(GAIL)":[4],"\u2014":[5,89,101],"a":[6],"general":[7],"model-free":[8],"method,":[11],"allows":[12],"robots":[13],"to":[14,46,97,134],"directly":[15],"learn":[16],"policies":[17],"from":[18,59,84],"expert":[19],"trajectories":[20],"in":[21,78,122],"large":[22],"environments.":[23],"However,":[24],"GAIL":[25,70],"shares":[26],"the":[27,39,48,67,112,118],"limitation":[28],"of":[29,41,50,69,120],"other":[30],"methods":[33],"that":[34],"they":[35],"can":[36,115],"seldom":[37],"surpass":[38,117],"performance":[40,119],"demonstrations.":[42],"In":[43],"this":[44],"paper,":[45],"address":[47],"limit":[49],"GAIL,":[51],"we":[52],"propose":[53],"GAN-based":[54],"interactive":[55,72],"reinforcement":[56,73],"(GAIRL)":[58],"demonstrations":[60,121],"and":[61,71,94,106,125,128],"human":[62],"evaluative":[63],"feedback,":[64],"by":[65],"combining":[66],"advantages":[68],"learning.":[74],"We":[75],"test":[76],"GAIRL":[77,113],"six":[79],"physics-based":[80],"control":[81,87],"tasks,":[82],"ranging":[83],"simple":[85],"low-dimensional":[86,124],"tasks":[88,100,127],"Cart":[90],"Pole,":[91],"Mountain":[92],"Car":[93],"Lunar":[95],"Lander,":[96],"difficult":[98],"high-dimensional":[99,126],"Inverted":[102],"Double":[103],"Pendulum,":[104],"Hopper":[105],"HalfCheetah.":[107],"Our":[108],"results":[109],"suggest":[110],"that,":[111],"agent":[114],"generally":[116],"both":[123],"get":[129],"an":[130],"optimal":[131,135],"or":[132],"close":[133],"policy.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2021-04-26T00:00:00"}