Behavior monitoring under uncertainty using Bayesian surprise and optimal action selection

Autores
Avila, Luis Omar; Martinez, Ernesto Carlos
Año de publicación
2014
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
The increasing trend towards delegating tasks to autonomous artificial agents in safety–critical sociotechnical systems makes monitoring an action selection policy of paramount importance. Agent behavior monitoring may profit from a stochastic specification of an optimal policy under uncertainty. A probabilistic monitoring approach is proposed to assess if an agent behavior (or policy) respects its specification. The desired policy is modeled by a prior distribution for state transitions in an optimally-controlled stochastic process. Bayesian surprise is defined as the Kullback–Leibler divergence between the state transition distribution for the observed behavior and the distribution for optimal action selection. To provide a sensitive on-line estimation of Bayesian surprise with small samples twin Gaussian processes are used. Timely detection of a deviant behavior or anomaly in an artificial pancreas highlights the sensitivity of Bayesian surprise to a meaningful discrepancy regarding the stochastic optimal policy when there exist excessive glycemic variability, sensor errors, controller ill-tuning and infusion pump malfunctioning. To reject outliers and leave out redundant information, on-line sparsification of data streams is proposed.
Fil: Avila, Luis Omar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Desarrollo y Diseño. Universidad Tecnológica Nacional. Facultad Regional Santa Fe. Instituto de Desarrollo y Diseño; Argentina
Fil: Martinez, Ernesto Carlos. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Desarrollo y Diseño. Universidad Tecnológica Nacional. Facultad Regional Santa Fe. Instituto de Desarrollo y Diseño; Argentina
Materia
Bayesian Surprise
Artificial Pancreas
Behavior Monitoring
Optimal Action Selection
Kullback–Leibler Divergence
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/22441

id CONICETDig_5ed61723e341474479bba36d5c7fa27d
oai_identifier_str oai:ri.conicet.gov.ar:11336/22441
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Behavior monitoring under uncertainty using Bayesian surprise and optimal action selectionAvila, Luis OmarMartinez, Ernesto CarlosBayesian SurpriseArtificial PancreasBehavior MonitoringOptimal Action SelectionKullback–Leibler Divergencehttps://purl.org/becyt/ford/2.2https://purl.org/becyt/ford/2The increasing trend towards delegating tasks to autonomous artificial agents in safety–critical sociotechnical systems makes monitoring an action selection policy of paramount importance. Agent behavior monitoring may profit from a stochastic specification of an optimal policy under uncertainty. A probabilistic monitoring approach is proposed to assess if an agent behavior (or policy) respects its specification. The desired policy is modeled by a prior distribution for state transitions in an optimally-controlled stochastic process. Bayesian surprise is defined as the Kullback–Leibler divergence between the state transition distribution for the observed behavior and the distribution for optimal action selection. To provide a sensitive on-line estimation of Bayesian surprise with small samples twin Gaussian processes are used. Timely detection of a deviant behavior or anomaly in an artificial pancreas highlights the sensitivity of Bayesian surprise to a meaningful discrepancy regarding the stochastic optimal policy when there exist excessive glycemic variability, sensor errors, controller ill-tuning and infusion pump malfunctioning. To reject outliers and leave out redundant information, on-line sparsification of data streams is proposed.Fil: Avila, Luis Omar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Desarrollo y Diseño. Universidad Tecnológica Nacional. Facultad Regional Santa Fe. Instituto de Desarrollo y Diseño; ArgentinaFil: Martinez, Ernesto Carlos. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Desarrollo y Diseño. Universidad Tecnológica Nacional. Facultad Regional Santa Fe. Instituto de Desarrollo y Diseño; ArgentinaElsevier2014-05info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/22441Avila, Luis Omar; Martinez, Ernesto Carlos; Behavior monitoring under uncertainty using Bayesian surprise and optimal action selection; Elsevier; Expert Systems with Applications; 41; 14; 5-2014; 6327-63450957-4174CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.1016/j.eswa.2014.04.031info:eu-repo/semantics/altIdentifier/url/http://www.sciencedirect.com/science/article/pii/S0957417414002541info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-nd/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:29:52Zoai:ri.conicet.gov.ar:11336/22441instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:29:52.738CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Behavior monitoring under uncertainty using Bayesian surprise and optimal action selection
title Behavior monitoring under uncertainty using Bayesian surprise and optimal action selection
spellingShingle Behavior monitoring under uncertainty using Bayesian surprise and optimal action selection
Avila, Luis Omar
Bayesian Surprise
Artificial Pancreas
Behavior Monitoring
Optimal Action Selection
Kullback–Leibler Divergence
title_short Behavior monitoring under uncertainty using Bayesian surprise and optimal action selection
title_full Behavior monitoring under uncertainty using Bayesian surprise and optimal action selection
title_fullStr Behavior monitoring under uncertainty using Bayesian surprise and optimal action selection
title_full_unstemmed Behavior monitoring under uncertainty using Bayesian surprise and optimal action selection
title_sort Behavior monitoring under uncertainty using Bayesian surprise and optimal action selection
dc.creator.none.fl_str_mv Avila, Luis Omar
Martinez, Ernesto Carlos
author Avila, Luis Omar
author_facet Avila, Luis Omar
Martinez, Ernesto Carlos
author_role author
author2 Martinez, Ernesto Carlos
author2_role author
dc.subject.none.fl_str_mv Bayesian Surprise
Artificial Pancreas
Behavior Monitoring
Optimal Action Selection
Kullback–Leibler Divergence
topic Bayesian Surprise
Artificial Pancreas
Behavior Monitoring
Optimal Action Selection
Kullback–Leibler Divergence
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.2
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv The increasing trend towards delegating tasks to autonomous artificial agents in safety–critical sociotechnical systems makes monitoring an action selection policy of paramount importance. Agent behavior monitoring may profit from a stochastic specification of an optimal policy under uncertainty. A probabilistic monitoring approach is proposed to assess if an agent behavior (or policy) respects its specification. The desired policy is modeled by a prior distribution for state transitions in an optimally-controlled stochastic process. Bayesian surprise is defined as the Kullback–Leibler divergence between the state transition distribution for the observed behavior and the distribution for optimal action selection. To provide a sensitive on-line estimation of Bayesian surprise with small samples twin Gaussian processes are used. Timely detection of a deviant behavior or anomaly in an artificial pancreas highlights the sensitivity of Bayesian surprise to a meaningful discrepancy regarding the stochastic optimal policy when there exist excessive glycemic variability, sensor errors, controller ill-tuning and infusion pump malfunctioning. To reject outliers and leave out redundant information, on-line sparsification of data streams is proposed.
Fil: Avila, Luis Omar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Desarrollo y Diseño. Universidad Tecnológica Nacional. Facultad Regional Santa Fe. Instituto de Desarrollo y Diseño; Argentina
Fil: Martinez, Ernesto Carlos. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Desarrollo y Diseño. Universidad Tecnológica Nacional. Facultad Regional Santa Fe. Instituto de Desarrollo y Diseño; Argentina
description The increasing trend towards delegating tasks to autonomous artificial agents in safety–critical sociotechnical systems makes monitoring an action selection policy of paramount importance. Agent behavior monitoring may profit from a stochastic specification of an optimal policy under uncertainty. A probabilistic monitoring approach is proposed to assess if an agent behavior (or policy) respects its specification. The desired policy is modeled by a prior distribution for state transitions in an optimally-controlled stochastic process. Bayesian surprise is defined as the Kullback–Leibler divergence between the state transition distribution for the observed behavior and the distribution for optimal action selection. To provide a sensitive on-line estimation of Bayesian surprise with small samples twin Gaussian processes are used. Timely detection of a deviant behavior or anomaly in an artificial pancreas highlights the sensitivity of Bayesian surprise to a meaningful discrepancy regarding the stochastic optimal policy when there exist excessive glycemic variability, sensor errors, controller ill-tuning and infusion pump malfunctioning. To reject outliers and leave out redundant information, on-line sparsification of data streams is proposed.
publishDate 2014
dc.date.none.fl_str_mv 2014-05
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/22441
Avila, Luis Omar; Martinez, Ernesto Carlos; Behavior monitoring under uncertainty using Bayesian surprise and optimal action selection; Elsevier; Expert Systems with Applications; 41; 14; 5-2014; 6327-6345
0957-4174
CONICET Digital
CONICET
url http://hdl.handle.net/11336/22441
identifier_str_mv Avila, Luis Omar; Martinez, Ernesto Carlos; Behavior monitoring under uncertainty using Bayesian surprise and optimal action selection; Elsevier; Expert Systems with Applications; 41; 14; 5-2014; 6327-6345
0957-4174
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1016/j.eswa.2014.04.031
info:eu-repo/semantics/altIdentifier/url/http://www.sciencedirect.com/science/article/pii/S0957417414002541
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844614306316943360
score 13.070432