{"id":"https://openalex.org/W3089756717","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207622","title":"Improved Stochastic Synapse Reinforcement Learning for Continuous Actions in Sharply Changing Environments","display_name":"Improved Stochastic Synapse Reinforcement Learning for Continuous Actions in Sharply Changing Environments","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3089756717","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207622","mag":"3089756717"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5004370417","display_name":"Syed Naveed Hussain Shah","orcid":"https://orcid.org/0000-0002-7418-870X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Syed Naveed Hussain Shah","raw_affiliation_strings":["MS Office, Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"MS Office, Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061058579","display_name":"Dean F. Hougen","orcid":"https://orcid.org/0000-0001-5393-1480"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dean Frederick Hougen","raw_affiliation_strings":["Dept. of Computer Science, University of Oklahoma, Norman, OK, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of Oklahoma, Norman, OK, USA","institution_ids":["https://openalex.org/I8692664"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004370417"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.11672268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"8","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7167875170707703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6471826434135437},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6007104516029358},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5783344507217407},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5672919750213623},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5584993362426758},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5323793292045593},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.5198593735694885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.482740581035614},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3362944424152374},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2387695610523224}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7167875170707703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6471826434135437},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6007104516029358},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5783344507217407},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5672919750213623},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5584993362426758},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5323793292045593},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.5198593735694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.482740581035614},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3362944424152374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2387695610523224},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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":37,"referenced_works":["https://openalex.org/W1821722","https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1526455201","https://openalex.org/W1534474912","https://openalex.org/W1995118028","https://openalex.org/W2028526571","https://openalex.org/W2052117683","https://openalex.org/W2056531506","https://openalex.org/W2080759927","https://openalex.org/W2095894922","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2278679828","https://openalex.org/W2290354866","https://openalex.org/W2342662072","https://openalex.org/W2785774352","https://openalex.org/W2787512026","https://openalex.org/W2798741797","https://openalex.org/W2809162153","https://openalex.org/W2890624904","https://openalex.org/W2950471160","https://openalex.org/W2963641140","https://openalex.org/W2963864421","https://openalex.org/W3007295133","https://openalex.org/W3008620669","https://openalex.org/W3036997757","https://openalex.org/W4235358875","https://openalex.org/W4253365321","https://openalex.org/W6684921986","https://openalex.org/W6696324988","https://openalex.org/W6704571135","https://openalex.org/W6754148645","https://openalex.org/W6774239083","https://openalex.org/W6779275715"],"related_works":["https://openalex.org/W2789522126","https://openalex.org/W2066693961","https://openalex.org/W2368363778","https://openalex.org/W122584421","https://openalex.org/W4244295168","https://openalex.org/W2753351751","https://openalex.org/W3185180338","https://openalex.org/W2889348933","https://openalex.org/W2351643838","https://openalex.org/W3033677963"],"abstract_inverted_index":{"Reinforcement":[0,40,92],"learning":[1,41,130],"in":[2,19,35,42,126],"continuous":[3],"action":[4],"spaces":[5],"requires":[6],"mechanisms":[7],"that":[8,114],"allow":[9],"for":[10,62,83,89],"exploration":[11,26],"of":[12,25,53,106,117,123,128],"infinite":[13],"possible":[14,73],"actions.":[15],"One":[16],"challenging":[17],"issue":[18,31],"such":[20],"systems":[21],"is":[22,32],"the":[23],"amount":[24],"appropriate":[27,61],"during":[28],"learning.":[29],"This":[30],"complicated":[33],"further":[34],"sharply":[36],"changing":[37],"dynamic":[38],"environments.":[39],"artificial":[43],"neural":[44],"networks":[45],"with":[46],"multiparameter":[47],"distributions":[48],"can":[49],"address":[50],"all":[51],"aspects":[52],"these":[54,64,118],"issues.":[55],"However,":[56],"which":[57],"equations":[58,74,81,87,119,124],"are":[59],"most":[60],"updating":[63],"parameters":[65],"remains":[66],"an":[67],"open":[68],"question.":[69],"Here":[70],"we":[71,112],"consider":[72],"derived":[75],"from":[76],"two":[77],"sources:":[78],"The":[79],"classic":[80],"proposed":[82],"REINFORCE":[84],"and":[85,100,132],"modern":[86],"introduced":[88],"Stochastic":[90],"Synapse":[91],"Learning":[93],"(SSRL),":[94],"as":[95,97],"well":[96],"combinations":[98,116],"thereof":[99],"variations":[101],"thereon.":[102],"Using":[103],"a":[104],"set":[105,122],"multidimensional":[107],"robot":[108],"inverse":[109],"kinematics":[110],"problems,":[111],"find":[113],"novel":[115],"outperform":[120],"either":[121],"alone":[125],"terms":[127],"both":[129],"rate":[131],"consistency.":[133]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}