{"id":"https://openalex.org/W2164966957","doi":null,"title":"Hybrid Reinforcement Learning and Its Application to Biped Robot Control","display_name":"Hybrid Reinforcement Learning and Its Application to Biped Robot Control","publication_year":1997,"publication_date":"1997-12-01","ids":{"openalex":"https://openalex.org/W2164966957","mag":"2164966957"},"language":"en","primary_location":{"id":"mag:2164966957","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/1434-hybrid-reinforcement-learning-and-its-application-to-biped-robot-control.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5103825362","display_name":"Satoshi Yamada","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Yamada","raw_affiliation_strings":["Advanced Technology R&D Center, Mitsubishi Electric Corporation, Amagasaki, Hyogo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Technology R&D Center, Mitsubishi Electric Corporation, Amagasaki, Hyogo, Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Akira Watanabe","orcid":"https://orcid.org/0000-0002-4597-5325","observed_orcids":["https://orcid.org/0000-0002-4597-5325"]},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Watanabe","raw_affiliation_strings":["Advanced Technology R&D Center, Mitsubishi Electric Corporation, Amagasaki, Hyogo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4597-5325","affiliations":[{"raw_affiliation_string":"Advanced Technology R&D Center, Mitsubishi Electric Corporation, Amagasaki, Hyogo, Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"last","author":{"id":null,"display_name":"Michio Nakashima","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Michio Nakashima","raw_affiliation_strings":["Advanced Technology R&D Center, Mitsubishi Electric Corporation, Amagasaki, Hyogo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Technology R&D Center, Mitsubishi Electric Corporation, Amagasaki, Hyogo, Japan","institution_ids":["https://openalex.org/I4210133125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210133125"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"1071","last_page":"1077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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":0.9965999722480774,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.003100000089034438,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/hybrid-reinforcement-learning","display_name":"hybrid reinforcement learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/fast-learning","display_name":"fast learning","score":0.4569999873638153}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8784016966819763},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6582769751548767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6201984882354736},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5786535143852234},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5579168200492859},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.5293881297111511},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5065537691116333},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.49417784810066223},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4571916460990906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45287641882896423},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4506318271160126},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.37617993354797363},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.275683730840683},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.21955463290214539},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2164966957","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/1434-hybrid-reinforcement-learning-and-its-application-to-biped-robot-control.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1583833196","https://openalex.org/W1969420452","https://openalex.org/W1988071341","https://openalex.org/W1993740947","https://openalex.org/W2013815893","https://openalex.org/W2025653905","https://openalex.org/W2041367235","https://openalex.org/W2113913482","https://openalex.org/W2124175081","https://openalex.org/W2127036885","https://openalex.org/W2473732573"],"related_works":["https://openalex.org/W7162193874","https://openalex.org/W3199351557","https://openalex.org/W6964623966","https://openalex.org/W4303856597","https://openalex.org/W1994923984","https://openalex.org/W7098961187","https://openalex.org/W3193098515","https://openalex.org/W2967815054","https://openalex.org/W2585360762","https://openalex.org/W1512209549"],"abstract_inverted_index":{"A":[0],"learning":[1,9,17,24,43,69,99,103,138],"system":[2,44,139],"composed":[3],"of":[4,25,50,129],"linear":[5,85,118],"control":[6,27,35,49,58,78,86,89,123],"modules,":[7],"reinforcement":[8,16,68],"modules":[10,13,31],"and":[11],"selection":[12,30,106],"(a":[14],"hybrid":[15,42],"system)":[18],"is":[19,133,140],"proposed":[20],"for":[21],"the":[22,39,48,57,66,77,84,90,101,105,117,122,137],"fast":[23],"real-world":[26],"problems.":[28],"The":[29,126],"choose":[32],"one":[33],"appropriate":[34],"module":[36,87,107],"dependent":[37],"on":[38,59,79],"state.":[40],"This":[41],"was":[45,94,108],"applied":[46],"to":[47,75,142],"a":[51,60,80,97,111],"stilt-type":[52],"biped":[53],"robot.":[54,91],"It":[55],"learned":[56,121],"sloped":[61],"floor":[62],"more":[63,124],"quickly":[64],"than":[65],"usual":[67],"because":[70],"it":[71,93,120],"did":[72],"not":[73],"need":[74],"learn":[76],"flat":[81],"floor,":[82],"where":[83],"can":[88],"When":[92],"trained":[95,109],"by":[96,110,116],"2-step":[98],"(during":[100],"first":[102],"step,":[104],"training":[112],"procedure":[113],"controlled":[114],"only":[115],"controller),":[119],"quickly.":[125],"average":[127],"number":[128],"trials":[130],"(about":[131],"50)":[132],"so":[134],"small":[135],"that":[136],"applicable":[141],"real":[143],"robot":[144],"control.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2016-06-24T00:00:00"}