{"id":"https://openalex.org/W2835755340","doi":"https://doi.org/10.1145/3205651.3208295","title":"Model parameter adaptive instance-based policy optimization for episodic control tasks of nonholonomic systems","display_name":"Model parameter adaptive instance-based policy optimization for episodic control tasks of nonholonomic systems","publication_year":2018,"publication_date":"2018-07-06","ids":{"openalex":"https://openalex.org/W2835755340","doi":"https://doi.org/10.1145/3205651.3208295","mag":"2835755340"},"language":"en","primary_location":{"id":"doi:10.1145/3205651.3208295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3205651.3208295","pdf_url":null,"source":{"id":"https://openalex.org/S4363608771","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","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/A5087581945","display_name":"Ohashi Kyotaro","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162928","display_name":"\u014ctani University","ror":"https://ror.org/05b7rex33","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210162928"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kyotaro Ohashi","raw_affiliation_strings":["Shinshu University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shinshu University","institution_ids":["https://openalex.org/I4210162928"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080457354","display_name":"Natsuki Fujiyoshi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162928","display_name":"\u014ctani University","ror":"https://ror.org/05b7rex33","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210162928"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Natsuki Fujiyoshi","raw_affiliation_strings":["Shinshu University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shinshu University","institution_ids":["https://openalex.org/I4210162928"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089643881","display_name":"Naoki Sakamoto","orcid":"https://orcid.org/0000-0002-2794-6651"},"institutions":[{"id":"https://openalex.org/I4210162928","display_name":"\u014ctani University","ror":"https://ror.org/05b7rex33","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210162928"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Sakamoto","raw_affiliation_strings":["Shinshu University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shinshu University","institution_ids":["https://openalex.org/I4210162928"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038757231","display_name":"Youhei Akimoto","orcid":"https://orcid.org/0000-0003-2760-8123"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Youhei Akimoto","raw_affiliation_strings":["University of Tsukuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06683392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1426","last_page":"1433"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9970999956130981,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.7415005564689636},{"id":"https://openalex.org/keywords/cma-es","display_name":"CMA-ES","score":0.7297021150588989},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6563904881477356},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5436680912971497},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5405816435813904},{"id":"https://openalex.org/keywords/evolution-strategy","display_name":"Evolution strategy","score":0.5195636749267578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4942303001880646},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.4258017838001251},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41402238607406616},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.367609441280365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3442193269729614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15366894006729126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415005564689636},{"id":"https://openalex.org/C205555498","wikidata":"https://www.wikidata.org/wiki/Q505588","display_name":"CMA-ES","level":4,"score":0.7297021150588989},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6563904881477356},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5436680912971497},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5405816435813904},{"id":"https://openalex.org/C207002847","wikidata":"https://www.wikidata.org/wiki/Q2912857","display_name":"Evolution strategy","level":3,"score":0.5195636749267578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4942303001880646},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.4258017838001251},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41402238607406616},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.367609441280365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3442193269729614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15366894006729126},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3205651.3208295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3205651.3208295","pdf_url":null,"source":{"id":"https://openalex.org/S4363608771","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1515851193","https://openalex.org/W1565759249","https://openalex.org/W1578647949","https://openalex.org/W1914583973","https://openalex.org/W1994492573","https://openalex.org/W2016178266","https://openalex.org/W2058296799","https://openalex.org/W2079908035","https://openalex.org/W2111935653","https://openalex.org/W2116339921","https://openalex.org/W2119814172","https://openalex.org/W2123592613","https://openalex.org/W2258540759","https://openalex.org/W2312609093","https://openalex.org/W2325007205","https://openalex.org/W2596367596","https://openalex.org/W2604883922","https://openalex.org/W3147079603"],"related_works":["https://openalex.org/W1492325323","https://openalex.org/W1579744901","https://openalex.org/W2510724351","https://openalex.org/W3087341323","https://openalex.org/W2465356436","https://openalex.org/W2552260697","https://openalex.org/W2078076985","https://openalex.org/W2592891920","https://openalex.org/W2102869784","https://openalex.org/W2116954712"],"abstract_inverted_index":{"Evolutionary":[0],"Computation":[1],"(EC)":[2],"attracts":[3],"more":[4,6],"and":[5,63,91,128,169],"attention":[7],"in":[8,48,68,89],"Reinforcement":[9],"Learning":[10],"(RL)":[11],"with":[12,186],"successful":[13],"applications":[14],"such":[15,45,84],"as":[16,46,85],"robot":[17],"control.":[18],"Instance-Based":[19],"Policy":[20],"(IBP)":[21],"is":[22,79,106,139,154,184],"a":[23,120,140,155],"promising":[24],"alternative":[25],"to":[26,41,56,75,80,99,176],"policy":[27,43,73,157],"representations":[28,44],"based":[29,72],"on":[30],"Artificial":[31],"Neural":[32],"Networks":[33],"(ANNs).":[34],"The":[35,96,149],"IBP":[36,126],"has":[37],"been":[38],"reported":[39],"superior":[40],"continuous":[42,147],"ANNs":[47,90],"the":[49,86,92,100,103,107,125,131,161,166,177,180,182],"stabilization":[50],"control":[51],"of":[52,59,94,109,163],"non-holonomic":[53],"systems":[54],"due":[55],"its":[57,64],"nature":[58],"bang-bang":[60],"type":[61],"control,":[62],"understandability.":[65],"A":[66],"difficulty":[67],"applying":[69],"an":[70,76,187],"EC":[71],"optimization":[74,129],"RL":[77,122],"task":[78],"choose":[81],"appropriate":[82],"hyper-parameters":[83],"network":[87],"structure":[88],"parameters":[93],"EC.":[95],"same":[97],"applies":[98],"IBP,":[101],"where":[102],"critical":[104],"parameter":[105],"number":[108,162],"instances":[110,164,171],"that":[111,159,172],"determines":[112],"mode":[113],"flexibility.":[114],"In":[115,179],"this":[116],"paper,":[117],"we":[118],"propose":[119],"novel":[121],"method":[123],"combining":[124],"representation":[127],"by":[130],"Covariance":[132],"Matrix":[133],"Adaptation":[134],"Evolution":[135],"Strategy":[136],"(CMA-ES),":[137],"which":[138],"state-of-the-art":[141],"general-purpose":[142],"search":[143,158],"algorithm":[144],"for":[145],"black-box":[146],"optimization.":[148],"proposed":[150],"method,":[151],"called":[152],"IBP-CMA,":[153],"direct":[156],"adapts":[160],"during":[165],"learning":[167],"process":[168],"activates":[170],"do":[173],"not":[174],"contribute":[175],"output.":[178],"simulation,":[181],"IBP-CMA":[183],"compared":[185],"ANN-based":[188],"RL,":[189],"CMA-TWEANN.":[190]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}