Jove
Visualize
Contáctanos
JoVE
x logofacebook logolinkedin logoyoutube logo
ACERCA DE JoVE
Visión GeneralLiderazgoBlogCentro de Ayuda JoVE
AUTORES
Proceso de PublicaciónConsejo EditorialAlcance y PolíticasRevisión por ParesPreguntas FrecuentesEnviar
BIBLIOTECARIOS
TestimoniosSuscripcionesAccesoRecursosConsejo Asesor de BibliotecasPreguntas Frecuentes
INVESTIGACIÓN
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchivo
EDUCACIÓN
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualCentro de Recursos para ProfesoresSitio de Profesores
Términos y Condiciones de Uso
Política de Privacidad
Políticas

Videos de Conceptos Relacionados

Associative Learning01:27

Associative Learning

2.1K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
2.1K
Reinforcement01:23

Reinforcement

1.2K
Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
1.2K
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

4.2K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
4.2K
Primary and Secondary Reinforcers01:23

Primary and Secondary Reinforcers

1.8K
In psychology, reinforcement is a key concept in behavior modification. B.F. Skinner demonstrated this with his experiments involving rats in what is known as a Skinner box. The rats learned to press a lever to receive food, a primary reinforcer that fulfilled their innate need for nourishment.
Effective reinforcers for humans vary depending on the individual and the context. Primary reinforcers, such as food, water, sleep, shelter, and pleasure, have inherent value and satisfy basic biological...
1.8K
Reinforcement Schedules01:24

Reinforcement Schedules

743
Positive reinforcement is a powerful method for teaching new behaviors to both animals and humans. B.F. Skinner demonstrated this with his experiments using rats in a Skinner box. When a rat pressed a lever, it received a food pellet. This immediate reward encouraged the rat to repeat the behavior. This method, where a reward follows every instance of the behavior, is known as continuous reinforcement. It is highly effective for establishing new behaviors quickly.
Once a behavior is learned,...
743
Observational Learning01:12

Observational Learning

1.5K
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
1.5K

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por
Same author

Statistics and AI - A Fireside Conversation.

Harvard data science review·2026
Same authorSame journal

Dimension Reduction for Large-Scale Federated Data: Statistical Rate and Asymptotic Inference.

Journal of the American Statistical Association·2026
Same author

Predicting the timing of first sustained cognitive worsening in Alzheimer's disease using real-world clinical data and machine learning.

medRxiv : the preprint server for health sciences·2026
Same author

Nonparametric estimation of the total treatment effect with multiple outcomes in the presence of terminal events.

Biometrics·2026
Same author

Scalable Gaussian process regression via median posterior inference for estimating the health effects of an environmental mixture.

Biometrics·2026
Same author

Large-scale antibody reactome profiling identifies herpesvirus-autoantigen associations underlying chronic diseases.

Research square·2026
Same journal

Instrumental Variable Estimation of Marginal Structural Mean Models for Time-Varying Treatment.

Journal of the American Statistical Association·2026
Same journal

Semiparametric Joint Modeling for Survival Analysis with Longitudinal Covariates.

Journal of the American Statistical Association·2026
Same journal

Facilitating Heterogeneous Effect Estimation via Statistically Efficient Categorical Modifiers.

Journal of the American Statistical Association·2026
Same journal

Nonparametric Density Estimation of a Long-Term Trend from Repeated Semicontinuous Data.

Journal of the American Statistical Association·2026
Same journal

Functional Integrative Bayesian Analysis of High-dimensional Multiplatform Clinicogenomic Data.

Journal of the American Statistical Association·2026
Ver todos los artículos relacionados

Video Experimental Relacionado

Updated: May 5, 2026

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
08:05

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

6.2K

Aprendizaje por Refuerzo Federado Offline

Doudou Zhou1, Yufeng Zhang2, Aaron Sonabend-W1

  • 1Department of Biostatistics, Harvard T.H. Chan School of Public Health.

Journal of the American Statistical Association
|February 20, 2026
PubMed
Resumen
Este resumen es generado por máquina.

El aprendizaje por refuerzo federado offline (RL) permite la medicina personalizada utilizando datos sanitarios distribuidos. Este nuevo algoritmo optimiza las políticas de tratamiento de manera eficiente en múltiples sitios, logrando un rendimiento comparable al de los datos centralizados.

Palabras clave:
regímenes de tratamiento dinámicoregistros de salud electrónicosaprendizaje multifuente

Videos de Experimentos Relacionados

Last Updated: May 5, 2026

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
08:05

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

6.2K

Área de la Ciencia:

  • Inteligencia Artificial
  • Aprendizaje Automático
  • Informática Médica

Sus antecedentes:

  • La medicina personalizada requiere regímenes de tratamiento dinámico, que a menudo utilizan el aprendizaje por refuerzo offline (RL).
  • El intercambio de datos sanitarios sensibles entre instituciones está restringido debido a preocupaciones de privacidad y heterogeneidad de datos específica del sitio.
  • Los métodos existentes luchan por utilizar eficazmente los conjuntos de datos distribuidos para desarrollar estrategias de tratamiento sólidas.

Objetivo del estudio:

  • Desarrollar un novedoso marco de RL federado offline que aborde la privacidad y la heterogeneidad en los datos sanitarios multisitio.
  • Permitir el análisis de características a nivel de sitio dentro de un modelo unificado.
  • Diseñar un algoritmo eficiente en comunicación para optimizar regímenes de tratamiento dinámico.

Principales métodos:

  • Se propuso un modelo de proceso de decisión de Markov multisitio que acomoda efectos de sitio tanto homogéneos como heterogéneos.
  • Se desarrolló el primer algoritmo de optimización de políticas federadas para RL offline con complejidad de muestra garantizada.
  • El algoritmo requiere solo una ronda de comunicación a través del intercambio de estadísticas resumidas.

Principales resultados:

  • El algoritmo propuesto de RL federado offline demuestra garantías teóricas sobre la suboptimización de la política, comparable a los escenarios de datos centralizados.
  • Simulaciones extensas confirman la efectividad del algoritmo en el aprendizaje de políticas óptimas.
  • El método se aplicó con éxito a un conjunto de datos de sepsis multisitio.

Conclusiones:

  • El RL federado offline es un enfoque viable para la medicina personalizada con datos sanitarios privados y distribuidos.
  • El algoritmo propuesto ofrece una solución eficiente y efectiva para la optimización de regímenes de tratamiento multisitio.
  • Este trabajo facilita la aplicación clínica de técnicas avanzadas de RL en entornos sanitarios del mundo real.