{"id":"https://openalex.org/W2994477615","doi":"https://doi.org/10.1109/robio49542.2019.8961475","title":"Influences of Neural Network Structures on an Efficient Reinforcement Learning Policy Search","display_name":"Influences of Neural Network Structures on an Efficient Reinforcement Learning Policy Search","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2994477615","doi":"https://doi.org/10.1109/robio49542.2019.8961475","mag":"2994477615"},"language":"en","primary_location":{"id":"doi:10.1109/robio49542.2019.8961475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5015266587","display_name":"Wangshu Zhu","orcid":"https://orcid.org/0000-0003-1950-202X"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wangshu Zhu","raw_affiliation_strings":["ShanghaiTech University,School of Information Science and Technology,Shanghai,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Information Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007414540","display_name":"Andr\u00e9 Rosendo","orcid":"https://orcid.org/0000-0003-4062-5390"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andre Rosendo","raw_affiliation_strings":["ShanghaiTech University,School of Information Science and Technology,Shanghai,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Information Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015266587"],"corresponding_institution_ids":["https://openalex.org/I30809798"],"apc_list":null,"apc_paid":null,"fwci":0.1443,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60421808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2019","issue":null,"first_page":"1374","last_page":"1379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9901000261306763,"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":0.9829999804496765,"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":0.8434209227561951},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6917471289634705},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6847500801086426},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5977252721786499},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5742278099060059},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5458269119262695},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.489912211894989},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4811914563179016},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45930159091949463},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.459150493144989},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45375514030456543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42290911078453064},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4151510000228882},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34931832551956177},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1601462960243225},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09296983480453491}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8434209227561951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6917471289634705},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6847500801086426},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5977252721786499},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5742278099060059},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5458269119262695},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.489912211894989},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4811914563179016},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45930159091949463},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.459150493144989},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45375514030456543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42290911078453064},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4151510000228882},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34931832551956177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1601462960243225},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09296983480453491},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/robio49542.2019.8961475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},{"id":"mag:3041948610","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002262598165101","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1502922572","https://openalex.org/W1738827650","https://openalex.org/W1972063518","https://openalex.org/W1997543377","https://openalex.org/W2012392077","https://openalex.org/W2012587148","https://openalex.org/W2018705428","https://openalex.org/W2104733512","https://openalex.org/W2107386393","https://openalex.org/W2108598243","https://openalex.org/W2112036188","https://openalex.org/W2116468180","https://openalex.org/W2145339207","https://openalex.org/W2151965738","https://openalex.org/W2167117957","https://openalex.org/W2192203593","https://openalex.org/W2257979135","https://openalex.org/W2550848904","https://openalex.org/W2553303224","https://openalex.org/W2604883922","https://openalex.org/W2606327391","https://openalex.org/W2902907165","https://openalex.org/W2919115771","https://openalex.org/W2948211788","https://openalex.org/W3005581722","https://openalex.org/W3007384386","https://openalex.org/W4205513846","https://openalex.org/W6629804754","https://openalex.org/W6640290305","https://openalex.org/W6675823452","https://openalex.org/W6675999342","https://openalex.org/W6682262322","https://openalex.org/W6729956949"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2387968248","https://openalex.org/W2120821724","https://openalex.org/W2350715914","https://openalex.org/W2101175215","https://openalex.org/W2379529020","https://openalex.org/W2893549521","https://openalex.org/W2352322616","https://openalex.org/W2574438335","https://openalex.org/W4226311653"],"abstract_inverted_index":{"The":[0,23,62],"Black-box":[1],"Data-efficient":[2],"RObot":[3],"Policy":[4],"Search":[5],"algorithm,":[6],"also":[7],"known":[8],"as":[9,192],"Black-DROPS,":[10],"is":[11,25,64,73,163,178],"one":[12,89],"of":[13,32,34,60,83,158],"the":[14,29,39,44,50,69,77,81,87,111,141,155,172],"most":[15],"data-efficient":[16],"algorithms":[17],"for":[18,21],"Reinforcement":[19],"Learning":[20],"robotics.":[22],"algorithm":[24,63,67,112],"based":[26],"on":[27,140,145],"studying":[28],"dynamical":[30],"model":[31],"uncertainty":[33],"robots,":[35],"learning":[36],"and":[37,103,133,184],"optimizing":[38],"corresponding":[40],"policy":[41],"to":[42,98,119,136,160,168,190],"maximize":[43],"reward.":[45],"Black-DROPS":[46,144],"does":[47,93],"not":[48,94],"limit":[49],"reward":[51],"function,":[52],"so":[53],"it":[54],"can":[55],"have":[56,95],"a":[57,107,146,169],"wide":[58],"range":[59],"applications.":[61],"an":[65,115,185],"optimization":[66],"using":[68],"numerical":[70],"approach,":[71],"which":[72],"more":[74],"efficient":[75],"than":[76],"analytical":[78],"approach":[79],"in":[80,195],"case":[82],"multi-core":[84],"operation.":[85],"But":[86],"default":[88],"layer":[90],"neural":[91],"network":[92],"enough":[96],"power":[97],"meet":[99],"some":[100],"difficult":[101],"problems,":[102],"when":[104],"faced":[105],"with":[106],"high":[108],"dimensional":[109],"problem":[110],"will":[113],"take":[114],"unusually":[116],"long":[117],"time":[118,174],"solve":[120],"it.":[121],"In":[122],"this":[123],"paper,":[124],"we":[125,193],"explore":[126],"different":[127],"Neural":[128],"Network":[129],"structures":[130],"(layers,":[131],"neurons,":[132],"computer":[134],"cores)":[135],"study":[137],"their":[138],"influence":[139],"speed":[142],"from":[143],"Double":[147],"Inverted":[148],"Pendulum":[149],"simulation.":[150],"We":[151],"demonstrate":[152],"that":[153],"although":[154],"performance":[156],"(number":[157],"iterations":[159],"reach":[161],"optimality)":[162],"affected":[164,180],"by":[165,181],"structural":[166],"changes":[167],"lesser":[170],"extent,":[171],"computation":[173],"(time":[175],"per":[176],"iteration)":[177],"drastically":[179],"such":[182],"changes,":[183],"optimal":[186],"structure":[187],"size":[188],"seems":[189],"exist,":[191],"highlight":[194],"our":[196],"results.":[197]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}