{"id":"https://openalex.org/W4390481679","doi":"https://doi.org/10.1109/ssci52147.2023.10372067","title":"Uncertainty Quantification for Efficient and Risk-Sensitive Reinforcement Learning","display_name":"Uncertainty Quantification for Efficient and Risk-Sensitive Reinforcement Learning","publication_year":2023,"publication_date":"2023-12-05","ids":{"openalex":"https://openalex.org/W4390481679","doi":"https://doi.org/10.1109/ssci52147.2023.10372067"},"language":"en","primary_location":{"id":"doi:10.1109/ssci52147.2023.10372067","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ssci52147.2023.10372067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077856407","display_name":"Mohamed-Harith Ibrahim","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I3019848993","display_name":"Mines Saint-\u00c9tienne","ror":"https://ror.org/05a1dws80","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I205703379","https://openalex.org/I3019848993"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohamed-Harith Ibrahim","raw_affiliation_strings":["Univ. Clermont Auvergne, CNRS, UMR,Mines Saint-Etienne,Saint-Etienne,France,F-42023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Clermont Auvergne, CNRS, UMR,Mines Saint-Etienne,Saint-Etienne,France,F-42023","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I3019848993"]}]},{"author_position":"middle","author":{"id":null,"display_name":"St\u00e9phane Lecoeuche","orcid":null},"institutions":[{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"St\u00e9phane Lecoeuche","raw_affiliation_strings":["IMT Nord Europe, Institut Mines-Telecom, Univ. Lille, Centre for Digital Systems,Lille,France,F-59000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMT Nord Europe, Institut Mines-Telecom, Univ. Lille, Centre for Digital Systems,Lille,France,F-59000","institution_ids":["https://openalex.org/I205703379","https://openalex.org/I2279609970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030348427","display_name":"Jacques Boon\u00e6rt","orcid":"https://orcid.org/0000-0002-8594-6959"},"institutions":[{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jacques Boonaert","raw_affiliation_strings":["IMT Nord Europe, Institut Mines-Telecom, Univ. Lille, Centre for Digital Systems,Lille,France,F-59000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMT Nord Europe, Institut Mines-Telecom, Univ. Lille, Centre for Digital Systems,Lille,France,F-59000","institution_ids":["https://openalex.org/I205703379","https://openalex.org/I2279609970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112103292","display_name":"Mireille Batton\u2010Hubert","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I3019848993","display_name":"Mines Saint-\u00c9tienne","ror":"https://ror.org/05a1dws80","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I205703379","https://openalex.org/I3019848993"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mireille Batton-Hubert","raw_affiliation_strings":["Univ. Clermont Auvergne, CNRS, UMR,Mines Saint-Etienne,Saint-Etienne,France,F-42023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Clermont Auvergne, CNRS, UMR,Mines Saint-Etienne,Saint-Etienne,France,F-42023","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I3019848993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49957496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"16","issue":null,"first_page":"1429","last_page":"1434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976999759674072,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976999759674072,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9957000017166138,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9921000003814697,"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":0.8598988056182861},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6675668358802795},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6581197381019592},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5372979044914246},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.5162489414215088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4612196385860443},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4501835107803345},{"id":"https://openalex.org/keywords/risk-assessment","display_name":"Risk assessment","score":0.44839608669281006},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4348636865615845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43062594532966614},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.42086735367774963},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1348610520362854},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09716126322746277},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0758131742477417}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8598988056182861},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6675668358802795},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6581197381019592},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5372979044914246},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.5162489414215088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4612196385860443},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4501835107803345},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.44839608669281006},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4348636865615845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43062594532966614},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.42086735367774963},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1348610520362854},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09716126322746277},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0758131742477417},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ssci52147.2023.10372067","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ssci52147.2023.10372067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:emse-04378533v1","is_oa":false,"landing_page_url":"https://hal-emse.ccsd.cnrs.fr/emse-04378533","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI), Dec 2023, Mexico City, France. pp.1429-1434, ⟨10.1109/SSCI52147.2023.10372067⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1647779468","https://openalex.org/W1845972764","https://openalex.org/W2057218189","https://openalex.org/W2280163991","https://openalex.org/W2586067474","https://openalex.org/W2724169821","https://openalex.org/W2765302304","https://openalex.org/W2767313115","https://openalex.org/W2798705390","https://openalex.org/W2945850646","https://openalex.org/W2963864421","https://openalex.org/W2968104655","https://openalex.org/W2986399309","https://openalex.org/W2996868001","https://openalex.org/W3021267234","https://openalex.org/W3123216837","https://openalex.org/W3124816456","https://openalex.org/W3129049248","https://openalex.org/W3204567614","https://openalex.org/W4287810981","https://openalex.org/W4289258965","https://openalex.org/W4306679387","https://openalex.org/W4312564987","https://openalex.org/W6639175102","https://openalex.org/W6683300800","https://openalex.org/W6684921986","https://openalex.org/W6695011786","https://openalex.org/W6733118196","https://openalex.org/W6740092555","https://openalex.org/W6745497480","https://openalex.org/W6748839928","https://openalex.org/W6750645735","https://openalex.org/W6751629939","https://openalex.org/W6763305696","https://openalex.org/W6770012831","https://openalex.org/W6776837600","https://openalex.org/W6779594309","https://openalex.org/W6780571964","https://openalex.org/W6789305357","https://openalex.org/W6790740607","https://openalex.org/W6802202268"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W1991093342","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"In":[0,13,97],"complex":[1],"real-world":[2],"decision":[3],"problems,":[4],"ensuring":[5],"safety":[6],"and":[7,34,38,45,70,86,92,112],"addressing":[8],"uncertainties":[9,40],"are":[10],"crucial":[11],"aspects.":[12],"this":[14],"work,":[15],"we":[16],"present":[17],"an":[18],"uncertainty-aware":[19],"Reinforcement":[20],"Learning":[21],"agent":[22,103],"designed":[23],"for":[24,124],"risk-sensitive":[25,107],"applications":[26],"in":[27],"continuous":[28],"action":[29],"spaces.":[30],"Our":[31],"method":[32,78],"quantifies":[33],"leverages":[35],"both":[36,80],"epistemic":[37],"aleatoric":[39],"to":[41,46,57,104,121],"enhance":[42],"agent's":[43],"learning":[44],"incorporate":[47],"risk":[48,113,122],"assessment":[49],"into":[50],"decision-making":[51],"processes.":[52],"We":[53,74],"conduct":[54],"numerical":[55],"experiments":[56],"evaluate":[58],"our":[59,77],"work":[60],"on":[61,115],"a":[62,106,116],"modified":[63],"version":[64],"of":[65,119],"Lunar":[66],"Lander":[67],"with":[68],"variable":[69],"risky":[71],"landing":[72],"conditions.":[73],"show":[75],"that":[76,109],"outperforms":[79],"Deep":[81],"Deterministic":[82],"Policy":[83],"Gradient":[84],"(DDPG)":[85],"TD3":[87],"algorithms":[88],"by":[89],"reducing":[90],"collisions":[91],"having":[93],"significant":[94],"faster":[95],"training.":[96],"addition,":[98],"it":[99],"enables":[100],"the":[101,125],"trained":[102],"learn":[105],"policy":[108],"balances":[110],"performance":[111],"based":[114],"specific":[117],"level":[118],"sensitivity":[120],"required":[123],"task.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}