{"id":"https://openalex.org/W2221816161","doi":"https://doi.org/10.1109/humanoids.2015.7363503","title":"Local Update Dynamic Policy Programming in reinforcement learning of pneumatic artificial muscle-driven humanoid hand control","display_name":"Local Update Dynamic Policy Programming in reinforcement learning of pneumatic artificial muscle-driven humanoid hand control","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2221816161","doi":"https://doi.org/10.1109/humanoids.2015.7363503","mag":"2221816161"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2015.7363503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2015.7363503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","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/A5011048472","display_name":"Yunduan Cui","orcid":"https://orcid.org/0000-0001-5539-4260"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunduan Cui","raw_affiliation_strings":["Department of Business Administration, TEl of Thessaly, Larissa, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Business Administration, TEl of Thessaly, Larissa, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042074952","display_name":"Takamitsu Matsubara","orcid":"https://orcid.org/0000-0003-3545-4814"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takamitsu Matsubara","raw_affiliation_strings":["Department of Business Administration, TEl of Thessaly, Larissa, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Business Administration, TEl of Thessaly, Larissa, Greece","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087612281","display_name":"Kenji Sugimoto","orcid":"https://orcid.org/0000-0002-5149-5643"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenji Sugimoto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"12","issue":null,"first_page":"1083","last_page":"1089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9952999949455261,"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"}},{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.9793000221252441,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8822063207626343},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.8266843557357788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7316169738769531},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5875207185745239},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5679464340209961},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5499033331871033},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5072910189628601},{"id":"https://openalex.org/keywords/actuator","display_name":"Actuator","score":0.5053973197937012},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.48587435483932495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4560404419898987},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.45549947023391724},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.43132591247558594},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3242036700248718},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.27207326889038086},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.21858632564544678},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.15077775716781616},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11455294489860535},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0999445915222168}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8822063207626343},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.8266843557357788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7316169738769531},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5875207185745239},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5679464340209961},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5499033331871033},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5072910189628601},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.5053973197937012},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.48587435483932495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4560404419898987},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.45549947023391724},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.43132591247558594},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3242036700248718},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.27207326889038086},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.21858632564544678},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.15077775716781616},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11455294489860535},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0999445915222168},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids.2015.7363503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2015.7363503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE-RAS 15th 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":37,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W211888945","https://openalex.org/W1499669280","https://openalex.org/W1597173708","https://openalex.org/W1689445748","https://openalex.org/W1925816294","https://openalex.org/W1977655452","https://openalex.org/W2016765487","https://openalex.org/W2051620263","https://openalex.org/W2061861724","https://openalex.org/W2084202551","https://openalex.org/W2115519811","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2130179125","https://openalex.org/W2144446635","https://openalex.org/W2150923691","https://openalex.org/W2156378823","https://openalex.org/W2165558283","https://openalex.org/W2172968643","https://openalex.org/W2184874993","https://openalex.org/W2225766585","https://openalex.org/W2586680856","https://openalex.org/W2962901215","https://openalex.org/W3005581722","https://openalex.org/W3103182070","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6608631664","https://openalex.org/W6629881138","https://openalex.org/W6640290305","https://openalex.org/W6677508557","https://openalex.org/W6678114464","https://openalex.org/W6679486095","https://openalex.org/W6682330108","https://openalex.org/W6682443896","https://openalex.org/W6686563451"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W2952594763","https://openalex.org/W4285537323","https://openalex.org/W2090698372","https://openalex.org/W4383890581","https://openalex.org/W2921905705","https://openalex.org/W4233178034","https://openalex.org/W2003293420","https://openalex.org/W1574958246"],"abstract_inverted_index":{"Pneumatic":[0],"Artificial":[1],"Muscle":[2],"(PAM)":[3],"is":[4],"an":[5,12,87],"attractive":[6],"device":[7],"to":[8,39,61,105,135],"be":[9],"used":[10],"as":[11,86],"actuator":[13],"for":[14],"humanoid":[15,152],"robots":[16,35,67],"because":[17],"of":[18,33,43,64,71,89,99,103,146,165],"its":[19,50,72],"high":[20,41],"power-to-weight":[21],"ratio":[22],"and":[23,30,49,114],"good":[24],"flexibility.":[25],"However,":[26],"both":[27,112],"the":[28,31,40,62,97,108,123,128],"modeling":[29],"controlling":[32],"PAM-driven":[34,66,151],"are":[36],"challenging":[37],"due":[38],"nonlinearities":[42],"a":[44,65,76,142,150,167,170],"PAM's":[45],"air":[46],"pressure":[47],"dynamics":[48],"mechanical":[51],"structure.":[52],"This":[53,94],"paper":[54],"focuses":[55],"on":[56],"applying":[57],"Reinforcement":[58],"Learning":[59],"(RL)":[60],"control":[63,136,164],"without":[68],"our":[69,159],"knowledge":[70],"model.":[73],"We":[74,132],"propose":[75],"new":[77],"RL":[78,180],"algorithm,":[79],"Local":[80],"Update":[81],"Dynamic":[82,90],"Policy":[83,91],"Programming":[84,92],"(LUDPP),":[85],"extension":[88],"(DPP).":[93],"algorithm":[95,120],"exploits":[96],"nature":[98],"smooth":[100],"policy":[101],"update":[102],"DPP":[104],"considerably":[106],"reduce":[107],"computational":[109,172],"complexity":[110],"in":[111],"time":[113],"space:":[115],"at":[116],"each":[117],"iteration,":[118],"this":[119],"only":[121],"updates":[122],"value":[124,177],"function":[125,178],"locally":[126],"throughout":[127],"whole":[129],"state-action":[130,144],"space.":[131],"applied":[133],"LUDPP":[134],"one":[137],"finger":[138],"(2":[139],"DOFs":[140],"with":[141,169],"12-dimensional":[143],"space)":[145],"Shadow":[147],"Dexterous":[148],"Hand,":[149],"robot":[153,168],"hand.":[154],"Experimental":[155],"results":[156],"suggest":[157],"that":[158],"method":[160],"can":[161],"achieve":[162],"successful":[163],"such":[166],"limited":[171],"resource":[173],"whereas":[174],"other":[175],"conventional":[176],"based":[179],"algorithms":[181],"(DPP,":[182],"LSPI)":[183],"cannot.":[184]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}