{"id":"https://openalex.org/W4402261840","doi":"https://doi.org/10.23919/acc60939.2024.10644690","title":"Data-Efficient Uncertainty-Guided Model-Based Reinforcement Learning with Unscented Kalman Bayesian Neural Networks","display_name":"Data-Efficient Uncertainty-Guided Model-Based Reinforcement Learning with Unscented Kalman Bayesian Neural Networks","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4402261840","doi":"https://doi.org/10.23919/acc60939.2024.10644690"},"language":"en","primary_location":{"id":"doi:10.23919/acc60939.2024.10644690","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc60939.2024.10644690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","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/A5023442148","display_name":"Xinyang Wu","orcid":"https://orcid.org/0000-0002-8912-2041"},"institutions":[{"id":"https://openalex.org/I3018473509","display_name":"Fraunhofer Institute for Manufacturing Engineering and Automation","ror":"https://ror.org/01rvqha10","country_code":"DE","type":"facility","lineage":["https://openalex.org/I3018473509","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Xinyang Wu","raw_affiliation_strings":["Fraunhofer IPA,Department Cyber Cognitive Intelligence (CCI)"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IPA,Department Cyber Cognitive Intelligence (CCI)","institution_ids":["https://openalex.org/I3018473509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092005272","display_name":"Elisabeth Wedernikow","orcid":null},"institutions":[{"id":"https://openalex.org/I3018473509","display_name":"Fraunhofer Institute for Manufacturing Engineering and Automation","ror":"https://ror.org/01rvqha10","country_code":"DE","type":"facility","lineage":["https://openalex.org/I3018473509","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Elisabeth Wedernikow","raw_affiliation_strings":["Fraunhofer IPA,Department Cyber Cognitive Intelligence (CCI)"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IPA,Department Cyber Cognitive Intelligence (CCI)","institution_ids":["https://openalex.org/I3018473509"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031354877","display_name":"Marco F. Huber","orcid":"https://orcid.org/0000-0002-8250-2092"},"institutions":[{"id":"https://openalex.org/I3018473509","display_name":"Fraunhofer Institute for Manufacturing Engineering and Automation","ror":"https://ror.org/01rvqha10","country_code":"DE","type":"facility","lineage":["https://openalex.org/I3018473509","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco F. Huber","raw_affiliation_strings":["Fraunhofer IPA,Department Cyber Cognitive Intelligence (CCI)"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IPA,Department Cyber Cognitive Intelligence (CCI)","institution_ids":["https://openalex.org/I3018473509"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023442148"],"corresponding_institution_ids":["https://openalex.org/I3018473509"],"apc_list":null,"apc_paid":null,"fwci":0.3488,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58321238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9983000159263611,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973000288009644,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9947999715805054,"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/kalman-filter","display_name":"Kalman filter","score":0.7944701313972473},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7116827964782715},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6691087484359741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6024051904678345},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5776326656341553},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5114861726760864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5082128047943115}],"concepts":[{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.7944701313972473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7116827964782715},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6691087484359741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6024051904678345},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5776326656341553},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5114861726760864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5082128047943115}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/acc60939.2024.10644690","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc60939.2024.10644690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/498090","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/498090","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W182452766","https://openalex.org/W2020934227","https://openalex.org/W2020999234","https://openalex.org/W2046633936","https://openalex.org/W2051434435","https://openalex.org/W2056760934","https://openalex.org/W2104533781","https://openalex.org/W2145339207","https://openalex.org/W2480512873","https://openalex.org/W2490662969","https://openalex.org/W2575705757","https://openalex.org/W2583993537","https://openalex.org/W2594728989","https://openalex.org/W2963238274","https://openalex.org/W2964059111","https://openalex.org/W3090211586","https://openalex.org/W3100944043","https://openalex.org/W3118641060","https://openalex.org/W3170059879","https://openalex.org/W4287813746","https://openalex.org/W4294562888","https://openalex.org/W4299828299","https://openalex.org/W4361006641","https://openalex.org/W4383108739","https://openalex.org/W4385360524","https://openalex.org/W6675740164","https://openalex.org/W6680657880","https://openalex.org/W6684578138","https://openalex.org/W6730042731","https://openalex.org/W6740033195","https://openalex.org/W6776324445","https://openalex.org/W6795014841","https://openalex.org/W6802035731","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"reinforcement":[3],"learning":[4,32],"(RL)":[5],"has":[6],"made":[7],"substantial":[8],"progress":[9],"by":[10],"providing":[11],"feasible":[12],"solutions":[13],"to":[14,50,75,100],"many":[15],"planning":[16],"and":[17,83],"control":[18,81,110],"problems.":[19],"However,":[20],"the":[21,41,44,65,71,80,86,91],"majority":[22],"of":[23,43,56,64],"RL":[24],"algorithms,":[25],"particularly":[26],"model-free":[27],"RL,":[28],"suffer":[29],"from":[30,59],"low":[31],"efficiency.":[33],"To":[34],"address":[35],"this":[36,38],"issue,":[37],"paper":[39],"proposes":[40],"utilization":[42],"Kalman":[45,73],"Bayesian":[46],"neural":[47],"network":[48],"(KBNN)":[49],"learn":[51],"a":[52,57,97,113],"tractable":[53],"dynamics":[54],"model":[55],"system":[58,66],"data":[60],"that":[61],"captures":[62],"uncertainties":[63,78,88],"state.":[67],"Additionally,":[68],"we":[69,84],"employ":[70],"unscented":[72],"filter":[74],"propagate":[76],"these":[77],"over":[79],"horizon,":[82],"exploit":[85],"propagated":[87],"explicitly":[89],"in":[90,103,112],"cost":[92],"function.":[93],"This":[94,105],"approach":[95],"presents":[96],"novel":[98],"solution":[99],"improve":[101],"data-efficiency":[102],"RL.":[104],"is":[106],"validated":[107],"on":[108],"classic":[109],"problems":[111],"comparative":[114],"analysis":[115],"against":[116],"state-of-the-art":[117],"methods.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}