{"id":"https://openalex.org/W3111442723","doi":"https://doi.org/10.1109/isse49799.2020.9272245","title":"Optimized Deep Reinforcement Learning Approach for Dynamic System","display_name":"Optimized Deep Reinforcement Learning Approach for Dynamic System","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3111442723","doi":"https://doi.org/10.1109/isse49799.2020.9272245","mag":"3111442723"},"language":"en","primary_location":{"id":"doi:10.1109/isse49799.2020.9272245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isse49799.2020.9272245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Systems Engineering (ISSE)","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/A5070733346","display_name":"Ziya Tan","orcid":"https://orcid.org/0000-0003-2813-5882"},"institutions":[{"id":"https://openalex.org/I176037994","display_name":"Erzincan University","ror":"https://ror.org/02h1e8605","country_code":"TR","type":"education","lineage":["https://openalex.org/I176037994"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Ziya Tan","raw_affiliation_strings":["Erzincan Binali Y\u0131ld\u0131r\u0131m University, Erzincan, Turkey"],"affiliations":[{"raw_affiliation_string":"Erzincan Binali Y\u0131ld\u0131r\u0131m University, Erzincan, Turkey","institution_ids":["https://openalex.org/I176037994"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082965948","display_name":"Mehmet Karak\u00f6se","orcid":"https://orcid.org/0000-0002-3276-3788"},"institutions":[{"id":"https://openalex.org/I143396566","display_name":"F\u0131rat University","ror":"https://ror.org/05teb7b63","country_code":"TR","type":"education","lineage":["https://openalex.org/I143396566"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mehmet Karakose","raw_affiliation_strings":["Firat University, Elazi\u011f, Turkey"],"affiliations":[{"raw_affiliation_string":"Firat University, Elazi\u011f, Turkey","institution_ids":["https://openalex.org/I143396566"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070733346"],"corresponding_institution_ids":["https://openalex.org/I176037994"],"apc_list":null,"apc_paid":null,"fwci":1.0605,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82625711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9621999859809875,"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":0.9445000290870667,"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":0.9476110339164734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7975922226905823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7305365800857544},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.5529294013977051},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5482467412948608},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5461652278900146},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5454651713371277},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5300428867340088},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4797574281692505},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45666036009788513},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42658495903015137},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41012951731681824},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10370969772338867}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9476110339164734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7975922226905823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7305365800857544},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.5529294013977051},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5482467412948608},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5461652278900146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5454651713371277},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5300428867340088},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4797574281692505},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45666036009788513},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42658495903015137},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41012951731681824},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10370969772338867},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isse49799.2020.9272245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isse49799.2020.9272245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Systems Engineering (ISSE)","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":18,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W112971866","https://openalex.org/W1566652554","https://openalex.org/W2121863487","https://openalex.org/W2173248099","https://openalex.org/W2765833400","https://openalex.org/W2883532348","https://openalex.org/W2888235455","https://openalex.org/W2908261578","https://openalex.org/W2963864421","https://openalex.org/W2987244635","https://openalex.org/W3010768390","https://openalex.org/W3033384842","https://openalex.org/W3156714352","https://openalex.org/W3209101326","https://openalex.org/W4214717370","https://openalex.org/W4242457953","https://openalex.org/W6794188299"],"related_works":["https://openalex.org/W1966456942","https://openalex.org/W2754028433","https://openalex.org/W3148138296","https://openalex.org/W1882507001","https://openalex.org/W2367922714","https://openalex.org/W2352650970","https://openalex.org/W2534140487","https://openalex.org/W4383501708","https://openalex.org/W2130711276","https://openalex.org/W2041126907"],"abstract_inverted_index":{"Reinforcement":[0,59,63],"learning":[1,42,45,130],"methods":[2],"provide":[3],"significant":[4],"and":[5,18,82,102],"impressive":[6],"improvements":[7],"in":[8,12,16,68,73,133],"artificial":[9],"intelligence":[10],"studies":[11],"recent":[13],"years,":[14],"especially":[15],"Atari":[17],"Go":[19],"games.":[20],"This":[21,56],"development":[22],"attracts":[23],"the":[24,37,116,125,134,137,148,152,166,169],"attention":[25],"of":[26,40,118,124,168],"scientists":[27],"who":[28],"try":[29],"to":[30,79,109,146],"understand":[31],"how":[32],"people":[33],"learn.":[34],"In":[35,111],"addition,":[36],"biggest":[38],"advantage":[39],"reinforcement":[41,129],"over":[43],"other":[44],"algorithms":[46,131],"is":[47,65,90,105],"that":[48,164],"it":[49,104],"does":[50],"not":[51],"require":[52],"any":[53],"prior":[54],"data.":[55],"feature":[57],"distinguishes":[58],"Learning":[60,64],"from":[61],"others.":[62],"an":[66,157],"approach":[67],"which":[69,107],"smart":[70],"programs":[71],"work":[72],"a":[74,94,98,143,162],"certain":[75],"or":[76,96],"uncertain":[77],"environment":[78],"constantly":[80],"adapt":[81],"learn":[83],"based":[84,127],"on":[85,136],"scoring.":[86],"The":[87],"feedback":[88],"process":[89],"also":[91,141],"known":[92],"as":[93],"reward":[95],"called":[97],"penalty.":[99],"Given":[100],"Agents":[101],"environment,":[103],"determined":[106],"action":[108],"take.":[110],"this":[112],"study,":[113],"we":[114],"apply":[115],"success":[117,150],"Deep":[119],"Q-Learning":[120],"(DQL)":[121],"algorithm,":[122],"one":[123],"model-free":[126],"deep":[128],"used":[132],"literature,":[135],"CartPole":[138],"problem.":[139],"We":[140,155],"offer":[142],"different":[144],"method":[145],"improve":[147],"agent's":[149],"during":[151],"training":[153],"phase.":[154],"present":[156],"optimized":[158],"DQL":[159],"algorithm":[160],"using":[161],"function":[163],"updates":[165],"weights":[167],"neural":[170],"network":[171],"at":[172],"every":[173],"step.":[174]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}