{"id":"https://openalex.org/W4311377987","doi":"https://doi.org/10.3390/s22249811","title":"Reinforcement Learning with Side Information for the Uncertainties","display_name":"Reinforcement Learning with Side Information for the Uncertainties","publication_year":2022,"publication_date":"2022-12-14","ids":{"openalex":"https://openalex.org/W4311377987","doi":"https://doi.org/10.3390/s22249811","pmid":"https://pubmed.ncbi.nlm.nih.gov/36560180"},"language":"en","primary_location":{"id":"doi:10.3390/s22249811","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22249811","pdf_url":"https://www.mdpi.com/1424-8220/22/24/9811/pdf?version=1671005656","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/22/24/9811/pdf?version=1671005656","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035669691","display_name":"Janghoon Yang","orcid":"https://orcid.org/0000-0002-4073-6747"},"institutions":[{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Janghoon Yang","raw_affiliation_strings":["Department of A.I. Software Engineering, Seoul Media Institute of Technology, Seoul 07590, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-4073-6747","affiliations":[{"raw_affiliation_string":"Department of A.I. Software Engineering, Seoul Media Institute of Technology, Seoul 07590, Republic of Korea","institution_ids":["https://openalex.org/I4210164379"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5035669691"],"corresponding_institution_ids":["https://openalex.org/I4210164379"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16106681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"24","first_page":"9811","last_page":"9811"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9926000237464905,"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":0.9232492446899414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6729251742362976},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6300520300865173},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.5826953649520874},{"id":"https://openalex.org/keywords/sliding-mode-control","display_name":"Sliding mode control","score":0.4697682559490204},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.46427056193351746},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.43963152170181274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4094548523426056},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.40817955136299133},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3547711670398712},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17850849032402039},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.1187024712562561}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9232492446899414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6729251742362976},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6300520300865173},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.5826953649520874},{"id":"https://openalex.org/C36662352","wikidata":"https://www.wikidata.org/wiki/Q6008560","display_name":"Sliding mode control","level":3,"score":0.4697682559490204},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.46427056193351746},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.43963152170181274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4094548523426056},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40817955136299133},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3547711670398712},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17850849032402039},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.1187024712562561},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.3390/s22249811","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22249811","pdf_url":"https://www.mdpi.com/1424-8220/22/24/9811/pdf?version=1671005656","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:36560180","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36560180","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9786629","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9786629","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:b3603212ddbb468ebca8a3390ce68644","is_oa":true,"landing_page_url":"https://doaj.org/article/b3603212ddbb468ebca8a3390ce68644","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":"Sensors, Vol 22, Iss 24, p 9811 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/24/9811/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22249811","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 22; Issue 24; Pages: 9811","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s22249811","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22249811","pdf_url":"https://www.mdpi.com/1424-8220/22/24/9811/pdf?version=1671005656","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G3064092315","display_name":null,"funder_award_id":"NRF-2020S1A5A2A03045921","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8588054344","display_name":null,"funder_award_id":"NRF-2017R1A2B4007398","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311377987.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1974101992","https://openalex.org/W2023233398","https://openalex.org/W2027312076","https://openalex.org/W2064770819","https://openalex.org/W2067897909","https://openalex.org/W2103431674","https://openalex.org/W2105579141","https://openalex.org/W2107396783","https://openalex.org/W2110428861","https://openalex.org/W2171215799","https://openalex.org/W2320262435","https://openalex.org/W2460629480","https://openalex.org/W2580285065","https://openalex.org/W2746649019","https://openalex.org/W2762015288","https://openalex.org/W2782096990","https://openalex.org/W2786933610","https://openalex.org/W2787938642","https://openalex.org/W2799899844","https://openalex.org/W2887056865","https://openalex.org/W2920004038","https://openalex.org/W2922520136","https://openalex.org/W3030037806","https://openalex.org/W3143014170","https://openalex.org/W3175550459","https://openalex.org/W3203292997","https://openalex.org/W4224273785","https://openalex.org/W4285295214","https://openalex.org/W4294199075","https://openalex.org/W6719071598","https://openalex.org/W6731818823"],"related_works":["https://openalex.org/W2022544890","https://openalex.org/W2394097730","https://openalex.org/W2769996735","https://openalex.org/W2043523297","https://openalex.org/W2260963831","https://openalex.org/W4235249401","https://openalex.org/W2331305369","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W2734546921"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2],"been":[3],"a":[4,11,28,66,74],"growing":[5],"interest":[6],"in":[7,17,35,56,70,111],"the":[8,36,47,57,77,99,114],"consensus":[9,87],"of":[10,38,59,113],"multi-agent":[12],"system":[13],"(MAS)":[14],"with":[15],"advances":[16],"artificial":[18],"intelligence":[19],"and":[20,108],"distributed":[21],"computing.":[22],"Sliding":[23],"mode":[24,93,101],"control":[25,34],"(SMC)":[26],"is":[27,63],"well-known":[29],"method":[30],"that":[31,98],"provides":[32],"robust":[33],"presence":[37],"uncertainties.":[39],"While":[40],"our":[41],"previous":[42],"study":[43],"introduced":[44,64],"SMC":[45,62],"to":[46,65,90],"reinforcement":[48],"learning":[49],"(RL)":[50],"based":[51],"on":[52],"approximate":[53],"dynamic":[54],"programming":[55],"context":[58],"optimal":[60],"control,":[61],"conventional":[67],"RL":[68,102,106],"framework":[69],"this":[71],"work.":[72],"As":[73],"specific":[75],"realization,":[76],"modified":[78],"twin":[79],"delayed":[80],"deep":[81],"deterministic":[82],"policy":[83],"gradient":[84],"(DDPG)":[85],"for":[86],"was":[88],"exploited":[89],"develop":[91],"sliding":[92,100],"RL.":[94],"Numerical":[95],"experiments":[96],"show":[97],"outperforms":[103],"existing":[104],"state-of-the-art":[105],"methods":[107,110],"model-based":[109],"terms":[112],"mean":[115],"square":[116],"error":[117],"(MSE)":[118],"performance.":[119]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
