{"id":"https://openalex.org/W3012370795","doi":"https://doi.org/10.1109/humanoids43949.2019.9034991","title":"Generative Adversarial Imitation Learning with Deep P-Network for Robotic Cloth Manipulation","display_name":"Generative Adversarial Imitation Learning with Deep P-Network for Robotic Cloth Manipulation","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W3012370795","doi":"https://doi.org/10.1109/humanoids43949.2019.9034991","mag":"3012370795"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids43949.2019.9034991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids43949.2019.9034991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-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/A5056162412","display_name":"Yoshihisa Tsurumine","orcid":"https://orcid.org/0000-0002-1514-1135"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihisa Tsurumine","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011048472","display_name":"Yunduan Cui","orcid":"https://orcid.org/0000-0001-5539-4260"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yunduan Cui","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035229636","display_name":"Kimitoshi Yamazaki","orcid":"https://orcid.org/0000-0002-4096-3288"},"institutions":[{"id":"https://openalex.org/I137975476","display_name":"Shinshu University","ror":"https://ror.org/0244rem06","country_code":"JP","type":"education","lineage":["https://openalex.org/I137975476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kimitoshi Yamazaki","raw_affiliation_strings":["Mechatronics Systems Engineering, Faculty of Engineering, Shinshu University, Nagano, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mechatronics Systems Engineering, Faculty of Engineering, Shinshu University, Nagano, Japan","institution_ids":["https://openalex.org/I137975476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042074952","display_name":"Takamitsu Matsubara","orcid":"https://orcid.org/0000-0003-3545-4814"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takamitsu Matsubara","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0245,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.90328879,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"274","last_page":"280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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":0.9977999925613403,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9897000193595886,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7691545486450195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7268519997596741},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7256436944007874},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7239983081817627},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.697113573551178},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5714817047119141},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5184047222137451},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49551093578338623},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.42838332056999207},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.424015074968338},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.42210957407951355},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07284650206565857}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7691545486450195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7268519997596741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7256436944007874},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7239983081817627},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.697113573551178},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5714817047119141},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5184047222137451},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49551093578338623},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.42838332056999207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.424015074968338},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.42210957407951355},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07284650206565857},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids43949.2019.9034991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids43949.2019.9034991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1501226982","https://openalex.org/W1520597402","https://openalex.org/W1771410628","https://openalex.org/W1949804828","https://openalex.org/W1982920857","https://openalex.org/W2001328977","https://openalex.org/W2042882799","https://openalex.org/W2099471712","https://openalex.org/W2121863487","https://openalex.org/W2130179125","https://openalex.org/W2155968351","https://openalex.org/W2501847708","https://openalex.org/W2530616813","https://openalex.org/W2554830522","https://openalex.org/W2558355904","https://openalex.org/W2575705757","https://openalex.org/W2587765586","https://openalex.org/W2594103415","https://openalex.org/W2729615412","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2746553466","https://openalex.org/W2789645218","https://openalex.org/W2796979132","https://openalex.org/W2892806280","https://openalex.org/W2900582619","https://openalex.org/W2919115771","https://openalex.org/W2949561945","https://openalex.org/W2950592907","https://openalex.org/W2963277051","https://openalex.org/W2964209830","https://openalex.org/W4214717370","https://openalex.org/W4302969537","https://openalex.org/W4320013936","https://openalex.org/W4322588822","https://openalex.org/W6638018090","https://openalex.org/W6679486095","https://openalex.org/W6718092244","https://openalex.org/W6734517396","https://openalex.org/W6741002519","https://openalex.org/W6741010574","https://openalex.org/W6742461812","https://openalex.org/W6750348766","https://openalex.org/W6751908871"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2502115930"],"abstract_inverted_index":{"Although":[0],"deep":[1,105],"Reinforcement":[2],"Learning":[3,43],"(RL)":[4],"has":[5],"been":[6],"successfully":[7,146],"applied":[8,134],"to":[9,54,135,151],"a":[10,91,101,127,136,143,148,152],"variety":[11],"of":[12,39,74,173],"tasks,":[13,49],"manually":[14],"designing":[15],"appropriate":[16],"reward":[17,66],"functions":[18],"for":[19,45,83],"such":[20],"complex":[21],"tasks":[22,87],"as":[23],"robotic":[24,46,84,176],"cloth":[25,47,85,177],"manipulation":[26,48,86],"still":[27],"remains":[28],"challenging":[29],"and":[30,61,116,145,158,165,170],"costly.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,89],"explore":[36],"an":[37,52],"approach":[38],"Generative":[40],"Adversarial":[41],"Imitation":[42],"(GAIL)":[44],"which":[50],"allows":[51],"agent":[53],"learn":[55],"near-optimal":[56],"behaviors":[57],"from":[58],"expert":[59],"demonstration":[60,154],"self":[62],"explorations":[63],"without":[64],"explicit":[65],"function":[67],"design.":[68],"Based":[69],"on":[70],"the":[71,79,114],"recent":[72],"success":[73],"value-function":[75,93,103],"based":[76,94,104],"RL":[77],"with":[78,141,155],"discrete":[80],"action":[81],"set":[82],"[1],":[88],"develop":[90],"novel":[92],"imitation":[95,167],"learning":[96,168],"framework,":[97],"P-GAIL.":[98],"P-GAIL":[99,132,174],"employs":[100],"modified":[102],"RL,":[106],"Entropy-maximizing":[107],"Deep":[108],"P-Network,":[109],"that":[110],"can":[111],"consider":[112],"both":[113,163],"smoothness":[115],"causal":[117],"entropy":[118],"in":[119,130,175],"policy":[120,149],"update.":[121],"After":[122],"investigating":[123],"its":[124],"effectiveness":[125],"through":[126],"toy":[128],"problem":[129],"simulation,":[131],"is":[133],"dual-arm":[137],"humanoid":[138],"robot":[139],"tasked":[140],"flipping":[142],"handkerchief":[144],"learns":[147],"close":[150],"human":[153],"limited":[156],"exploration":[157],"demonstration.":[159],"Experimental":[160],"results":[161],"suggest":[162],"fast":[164],"stable":[166],"ability":[169],"sample":[171],"efficiency":[172],"manipulation.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}