{"id":"https://openalex.org/W4415123955","doi":"https://doi.org/10.1109/access.2025.3621002","title":"AdvB-TD3: A Novel Decision-Making Framework for Complex Continuous Control Tasks","display_name":"AdvB-TD3: A Novel Decision-Making Framework for Complex Continuous Control Tasks","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415123955","doi":"https://doi.org/10.1109/access.2025.3621002"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3621002","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3621002","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3621002","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030353343","display_name":"Onur Osman","orcid":"https://orcid.org/0000-0001-7675-7999"},"institutions":[{"id":"https://openalex.org/I67581229","display_name":"Istanbul University","ror":"https://ror.org/03a5qrr21","country_code":"TR","type":"education","lineage":["https://openalex.org/I67581229"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Onur Osman","raw_affiliation_strings":["Electrical and Electronics Engineering Department, Istanbul Topkapi University, Istanbul, T&#x00FC;rkiye","Electrical and Electronics Engineering Department, Istanbul Topkapi University, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-7675-7999","affiliations":[{"raw_affiliation_string":"Electrical and Electronics Engineering Department, Istanbul Topkapi University, Istanbul, T&#x00FC;rkiye","institution_ids":["https://openalex.org/I67581229"]},{"raw_affiliation_string":"Electrical and Electronics Engineering Department, Istanbul Topkapi University, Istanbul, Turkey","institution_ids":["https://openalex.org/I67581229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036944001","display_name":"Tolga Kudret Karaca","orcid":null},"institutions":[{"id":"https://openalex.org/I53210213","display_name":"Istanbul Commerce University","ror":"https://ror.org/02v3kkq53","country_code":"TR","type":"education","lineage":["https://openalex.org/I53210213"]},{"id":"https://openalex.org/I67581229","display_name":"Istanbul University","ror":"https://ror.org/03a5qrr21","country_code":"TR","type":"education","lineage":["https://openalex.org/I67581229"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Tolga Kudret Karaca","raw_affiliation_strings":["Industrial Engineering Department, Istanbul Topkapi University, Istanbul, T&#x00FC;rkiye","Industrial Engineering Department, Istanbul Topkapi University, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-5562-6367","affiliations":[{"raw_affiliation_string":"Industrial Engineering Department, Istanbul Topkapi University, Istanbul, T&#x00FC;rkiye","institution_ids":["https://openalex.org/I53210213"]},{"raw_affiliation_string":"Industrial Engineering Department, Istanbul Topkapi University, Istanbul, Turkey","institution_ids":["https://openalex.org/I67581229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022659480","display_name":"Bahar Yal\u00e7\u0131n Kavu\u015f","orcid":"https://orcid.org/0000-0001-5295-1631"},"institutions":[{"id":"https://openalex.org/I250383648","display_name":"Izmir K\u00e2tip \u00c7elebi University","ror":"https://ror.org/024nx4843","country_code":"TR","type":"education","lineage":["https://openalex.org/I250383648"]},{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR","TR"],"is_corresponding":false,"raw_author_name":"Bahar Yalcin Kavus","raw_affiliation_strings":["Quality Coordination Office, &#x0130;zmir Katip &#x00C7;elebi University, &#x0130;zmir, T&#x00FC;rkiye","Quality Coordination Office, Rectorate, &#x0130;zmir Katip &#x00C7;elebi University, &#x0130;zmir, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-5295-1631","affiliations":[{"raw_affiliation_string":"Quality Coordination Office, &#x0130;zmir Katip &#x00C7;elebi University, &#x0130;zmir, T&#x00FC;rkiye","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Quality Coordination Office, Rectorate, &#x0130;zmir Katip &#x00C7;elebi University, &#x0130;zmir, Turkey","institution_ids":["https://openalex.org/I250383648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004614391","display_name":"G\u00f6kalp Tulum","orcid":"https://orcid.org/0000-0003-1906-0401"},"institutions":[{"id":"https://openalex.org/I67581229","display_name":"Istanbul University","ror":"https://ror.org/03a5qrr21","country_code":"TR","type":"education","lineage":["https://openalex.org/I67581229"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"G\u00f6kalp Tulum","raw_affiliation_strings":["Electrical and Electronics Engineering Department, Istanbul Topkapi University, Istanbul, T&#x00FC;rkiye","Electrical and Electronics Engineering Department, Istanbul Topkapi University, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0003-1906-0401","affiliations":[{"raw_affiliation_string":"Electrical and Electronics Engineering Department, Istanbul Topkapi University, Istanbul, T&#x00FC;rkiye","institution_ids":["https://openalex.org/I67581229"]},{"raw_affiliation_string":"Electrical and Electronics Engineering Department, Istanbul Topkapi University, Istanbul, Turkey","institution_ids":["https://openalex.org/I67581229"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.5421,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86925154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"13","issue":null,"first_page":"181675","last_page":"181685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.7013000249862671,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.7013000249862671,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.6079000234603882,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11810","display_name":"Complex Systems and Decision Making","score":0.5602999925613403,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8328999876976013},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6930000185966492},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6904000043869019},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5577999949455261},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5485000014305115},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4765999913215637},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46860000491142273},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.38679999113082886},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.36039999127388}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8328999876976013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755299985408783},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6930000185966492},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6904000043869019},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5577999949455261},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5485000014305115},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4043000042438507},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.36039999127388},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3621002","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3621002","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:dd21f6e9da3b4e0ab919cf3fdae0ccb1","is_oa":true,"landing_page_url":"https://doaj.org/article/dd21f6e9da3b4e0ab919cf3fdae0ccb1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 181675-181685 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3621002","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3621002","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,174],"has":[2],"emerged":[3],"as":[4,163,233],"a":[5,46,64,204,226,234],"transformative":[6],"approach":[7],"for":[8,207,240,247],"solving":[9],"complex":[10,178],"decision-making":[11,53,77,242],"problems,":[12,243],"particularly":[13,176],"in":[14,55,85,118,123,128,133,138,143,148,154,177,198,215],"continuous":[15,216],"action":[16],"domains.":[17,218],"In":[18],"this":[19],"study,":[20],"we":[21],"introduce":[22],"the":[23,36,186],"Advisory":[24],"Board":[25],"Twin":[26,37],"Delayed":[27,38],"Deep":[28,39],"Deterministic":[29,40],"Policy":[30,41],"Gradient":[31,42],"(AdvB-TD3)":[32],"framework,":[33],"which":[34],"integrates":[35],"(TD3)":[43],"algorithm":[44],"with":[45,244],"cooperative":[47],"advisory":[48],"board":[49],"structure":[50],"to":[51,158,189],"enhance":[52],"performance":[54,107,112],"dynamic":[56,69],"and":[57,68,75,105,150,166,173,183,212,222,237],"stochastic":[58],"environments.":[59,87],"The":[60,79],"AdvB-TD3":[61,92,110,169,202],"framework":[62],"employs":[63],"shared":[65],"critic":[66],"network":[67],"member":[70],"management,":[71],"enabling":[72],"robust,":[73,235],"adaptive,":[74],"scalable":[76,238],"processes.":[78],"proposed":[80],"methodology":[81],"was":[82],"rigorously":[83],"evaluated":[84],"MuJoCo":[86],"Experimental":[88],"results":[89],"demonstrated":[90,223],"that":[91],"consistently":[93],"outperformed":[94],"TD3":[95],"across":[96,193,225],"diverse":[97],"tasks,":[98],"achieving":[99],"faster":[100],"convergence,":[101],"higher":[102],"cumulative":[103],"rewards,":[104],"reduced":[106],"variability.":[108],"Specifically,":[109],"achieved":[111],"scores":[113],"of":[114,229],"309.3":[115],"\u00b1":[116,121,126,131,136,141,146,152],"0.95":[117],"BipedalWalker-v3,":[119],"4401.5":[120],"88.8":[122],"HalfCheetah-v4,":[124],"5303.5":[125],"26.0":[127],"Humanoid-v4,":[129],"1000":[130],"0.0":[132],"InvertedPendulum-v4,":[134],"9347.10":[135],"1.0":[137],"InvertedDoublePendulum-v4,":[139],"95.5":[140],"0.2":[142],"MountainCarContinuous-v0,":[144],"-130.1":[145],"81.5":[147],"Pendulum-v1,":[149],"317.0":[151],"4.2":[153],"Swimmer-v4.":[155],"When":[156],"compared":[157],"other":[159],"state-of-the-art":[160],"algorithms,":[161],"such":[162],"Q-Prop,":[164],"ACER,":[165],"Off-Policy":[167],"TRPO,":[168],"exhibited":[170],"superior":[171],"stability":[172],"efficiency,":[175],"environments":[179],"like":[180],"Bipedal":[181],"Walker":[182],"Humanoid.":[184],"Moreover,":[185],"framework\u2019s":[187],"ability":[188],"maintain":[190],"low":[191],"variability":[192],"trials":[194],"highlights":[195],"its":[196],"reliability":[197],"high-dimensional":[199,241],"tasks.":[200],"Overall,":[201],"establishes":[203],"new":[205],"benchmark":[206],"RL":[208],"methods,":[209],"outperforming":[210],"conventional":[211],"advanced":[213],"approaches":[214],"control":[217],"Its":[219],"innovative":[220],"architecture":[221],"superiority":[224],"wide":[227],"range":[228],"scenarios":[230],"position":[231],"it":[232],"efficient,":[236],"solution":[239],"significant":[245],"implications":[246],"advancing":[248],"AI-driven":[249],"systems.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-14T00:00:00"}
