{"id":"https://openalex.org/W4383108739","doi":"https://doi.org/10.1109/icra48891.2023.10160686","title":"Uncertainty-Guided Active Reinforcement Learning with Bayesian Neural Networks","display_name":"Uncertainty-Guided Active Reinforcement Learning with Bayesian Neural Networks","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108739","doi":"https://doi.org/10.1109/icra48891.2023.10160686"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/I4210127444","display_name":"Fraunhofer Institute for Cognitive Systems","ror":"https://ror.org/02fez3815","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127444","https://openalex.org/I4923324"]},{"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,Cyber Cognitive Intelligence Department","Cyber Cognitive Intelligence Department, Fraunhofer IPA"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IPA,Cyber Cognitive Intelligence Department","institution_ids":["https://openalex.org/I4210127444"]},{"raw_affiliation_string":"Cyber Cognitive Intelligence Department, Fraunhofer IPA","institution_ids":["https://openalex.org/I3018473509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031175358","display_name":"Mohamed El-Shamouty","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":"Mohamed El-Shamouty","raw_affiliation_strings":["Fraunhofer IPA,Robot and Assistive Systems Department","Robot and Assistive Systems Department, Fraunhofer IPA"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IPA,Robot and Assistive Systems Department","institution_ids":["https://openalex.org/I3018473509"]},{"raw_affiliation_string":"Robot and Assistive Systems Department, Fraunhofer IPA","institution_ids":["https://openalex.org/I3018473509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103622710","display_name":"Christof Nitsche","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"]},{"id":"https://openalex.org/I4210127444","display_name":"Fraunhofer Institute for Cognitive Systems","ror":"https://ror.org/02fez3815","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127444","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christof Nitsche","raw_affiliation_strings":["Fraunhofer IPA,Cyber Cognitive Intelligence Department","Cyber Cognitive Intelligence Department, Fraunhofer IPA"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IPA,Cyber Cognitive Intelligence Department","institution_ids":["https://openalex.org/I4210127444"]},{"raw_affiliation_string":"Cyber Cognitive Intelligence Department, Fraunhofer IPA","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"]},{"id":"https://openalex.org/I4210127444","display_name":"Fraunhofer Institute for Cognitive Systems","ror":"https://ror.org/02fez3815","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127444","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco F. Huber","raw_affiliation_strings":["Fraunhofer IPA,Cyber Cognitive Intelligence Department","Institute of Industrial Manufacturing and Management IFF, University of Stuttgart","Cyber Cognitive Intelligence Department, Fraunhofer IPA"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IPA,Cyber Cognitive Intelligence Department","institution_ids":["https://openalex.org/I4210127444"]},{"raw_affiliation_string":"Institute of Industrial Manufacturing and Management IFF, University of Stuttgart","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Cyber Cognitive Intelligence Department, Fraunhofer IPA","institution_ids":["https://openalex.org/I3018473509"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023442148"],"corresponding_institution_ids":["https://openalex.org/I3018473509","https://openalex.org/I4210127444"],"apc_list":null,"apc_paid":null,"fwci":1.0778,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83625395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5751","last_page":"5757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.9927999973297119,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8503081798553467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7474852800369263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7155004739761353},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6165140271186829},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5668019652366638},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.5413614511489868},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5284528732299805},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5172075033187866}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8503081798553467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474852800369263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7155004739761353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6165140271186829},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5668019652366638},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.5413614511489868},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5284528732299805},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5172075033187866}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra48891.2023.10160686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/472102","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/472102","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":69,"referenced_works":["https://openalex.org/W582134693","https://openalex.org/W1514463092","https://openalex.org/W1581808154","https://openalex.org/W1777239053","https://openalex.org/W1866206747","https://openalex.org/W1904365287","https://openalex.org/W1995875735","https://openalex.org/W2020999234","https://openalex.org/W2056760934","https://openalex.org/W2059448777","https://openalex.org/W2068194532","https://openalex.org/W2095705004","https://openalex.org/W2101234009","https://openalex.org/W2112462566","https://openalex.org/W2138309709","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2158782408","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2294567968","https://openalex.org/W2575705757","https://openalex.org/W2583993537","https://openalex.org/W2788781499","https://openalex.org/W2963092423","https://openalex.org/W2963095800","https://openalex.org/W2963238274","https://openalex.org/W2963864421","https://openalex.org/W2963977107","https://openalex.org/W2966555834","https://openalex.org/W3035847478","https://openalex.org/W3037939899","https://openalex.org/W3090211586","https://openalex.org/W3100944043","https://openalex.org/W3118641060","https://openalex.org/W3170059879","https://openalex.org/W3202239698","https://openalex.org/W4212863985","https://openalex.org/W4214717370","https://openalex.org/W4293864724","https://openalex.org/W4294562888","https://openalex.org/W4298132949","https://openalex.org/W4300799055","https://openalex.org/W6617145748","https://openalex.org/W6638088447","https://openalex.org/W6639216784","https://openalex.org/W6640036494","https://openalex.org/W6674330103","https://openalex.org/W6675354045","https://openalex.org/W6676789009","https://openalex.org/W6679529799","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6684578138","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6696879442","https://openalex.org/W6730042731","https://openalex.org/W6730111887","https://openalex.org/W6737327832","https://openalex.org/W6740801417","https://openalex.org/W6743806954","https://openalex.org/W6748523217","https://openalex.org/W6768581196","https://openalex.org/W6779651979","https://openalex.org/W6780559895","https://openalex.org/W6782527502","https://openalex.org/W6795014841"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,10,60,70,84,99],"Reinforcement":[3],"Learning":[4],"(RL)":[5],"have":[6],"made":[7],"significant":[8],"contributions":[9],"past":[11],"years":[12],"by":[13,31],"offering":[14],"intelligent":[15],"solutions":[16],"to":[17,49,55],"solve":[18],"robotic":[19,125],"tasks.":[20,126],"However,":[21],"most":[22],"RL":[23,61,118],"algorithms,":[24],"especially":[25],"the":[26,44,51,57,64,96,110,117],"model-free":[27],"RL,":[28],"are":[29],"plagued":[30],"low":[32],"learning":[33,58,111],"efficiency":[34,59,112],"and":[35,62,87,113],"safety":[36,68,105,114],"problems.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,94,108],"propose":[42],"using":[43],"Bayesian":[45],"Neural":[46],"Networks":[47],"(BNNs)":[48],"guide":[50],"agent":[52],"exploring":[53],"actively":[54],"enhance":[56],"investigate":[63],"potential":[65],"of":[66,80,116],"recognizing":[67],"risks":[69],"working":[71],"environments":[72,101],"with":[73,102,121],"uncertainty":[74,81,98],"information.":[75],"We":[76],"compare":[77],"two":[78],"types":[79],"quantification":[82],"methods":[83],"both":[85],"action":[86],"state":[88],"spaces.":[89],"To":[90],"validate":[91],"our":[92],"method,":[93],"visualize":[95],"quantified":[97],"robot":[100],"or":[103],"without":[104],"hazards.":[106],"Moreover,":[107],"evaluate":[109],"performance":[115],"agents":[119],"learned":[120],"BNNs":[122],"on":[123],"different":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}