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

Observational Learning01:12

Observational Learning

1.0K
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...
1.0K
Multi-Step Reactions02:31

Multi-Step Reactions

8.8K
Chemical reactions often occur in a stepwise fashion involving two or more distinct reactions taking place in a sequence. A balanced equation indicates the reacting species and the product species, but it reveals no details about how the reaction occurs at the molecular level. The reaction mechanism (or reaction path) provides details regarding the precise, step-by-step process by which a reaction occurs. Each of the steps in a reaction mechanism is called an elementary reaction. These...
8.8K
Reinforcement01:23

Reinforcement

934
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:
934
Reinforcements in Concrete01:25

Reinforcements in Concrete

478
Reinforced concrete is a composite material used extensively in construction, combining the compressive strength of concrete with the tensile strength of steel. This synergy is essential as concrete, while excellent at resisting compression, is weak under tension. Steel bars, or rebars, are embedded in the concrete to handle these tensile forces. The choice of steel is strategic; it shares a similar coefficient of thermal expansion with concrete, which ensures uniformity in response to...
478
Corrosion of Reinforcement01:27

Corrosion of Reinforcement

586
The corrosion of steel reinforcement within concrete is a process influenced by the material's inherent properties and external factors. The high pH level of around 13, provided by calcium hydroxide present in concrete, initially protects the steel reinforcement by promoting the formation of a passive iron oxide layer on its surface.
However, over time and under certain conditions like carbonation, chloride ingress, and cracking this protective state can be compromised. Steel has areas with...
586
Reinforcement Schedules01:24

Reinforcement Schedules

513
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,...
513

También podría leer

Artículos Relacionados

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

Ordenar por
Same author

Stakeholder Perspectives on Applying for the Fresh Fruit and Vegetable Program in Low-Resource Schools.

The Journal of school health·2026
Same author

Making Sense of Shoulder Exercise: Measuring the Accuracy of an Artificial Intelligence Model to Classify Shoulder Exercise via Wearable Sensors Among People With and Without Rotator Cuff Tendinopathy.

European journal of sport science·2026
Same author

The latent organization of white matter microstructure and its relation to fluid intelligence.

Imaging neuroscience (Cambridge, Mass.)·2026
Same author

The MEK-RAF molecular glue IK-595 has potent antitumor activity across RAS/MAPK pathway-altered cancers.

Nature cancer·2026
Same author

Electrophysiological resting-state signatures link polygenic scores to general intelligence.

Scientific reports·2025
Same author

Asparaginase Premedication With Hydrocortisone Decreases Hypersensitivity Reactions.

Journal of pediatric hematology/oncology·2025
Same journal

A boundary-regularization-enhanced video anomaly detection network based on context-adaptive spatio-temporal conditional diffusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

MT<sup>2</sup>-CSD and LLM-CRAN: A new dataset and an LLM-based multi-semantic knowledge fusion model for conversational stance detection.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TriAlignNet: A triple-path cross-modality alignment framework for multimodal time series forecasting.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Ver todos los artículos relacionados

Video Experimental Relacionado

Updated: Feb 9, 2026

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.9K

Multi-step first: Una estrategia de aprendizaje por refuerzo profundo ligera para un control continuo robusto con

Lingheng Meng1, Rob Gorbet2, Michael Burke3

  • 1Electrical and Computer Engineering, University of Waterloo, 200 University Avenue West, Waterloo, N2L 3G1, ON, Canada; Electrical and Computer Systems Engineering, Monash University, 18 Alliance Lane, Clayton, 3800, VIC, Australia; Data61, CSIRO, Research Way, Calyton, 3168, VIC, Australia.

Neural networks : the official journal of the International Neural Network Society
|February 7, 2026
PubMed
Resumen
Este resumen es generado por máquina.

Proximal Policy Optimization (PPO) muestra una mayor robustez en entornos parcialmente observables en comparación con Twin Delayed Deep Deterministic Policy Gradient (TD3) y Soft Actor-Critic (SAC). El bootstrapping de varios pasos en PPO y las adaptaciones a TD3/SAC mejoran el rendimiento en estos entornos desafiantes.

Palabras clave:
aprendizaje por refuerzo profundométodos de varios pasosproceso de decisión de Markov parcialmente observableaprendizaje de robots

Más Videos Relacionados

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.9K
The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents
09:01

The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents

Published on: July 8, 2015

13.1K

Videos de Experimentos Relacionados

Last Updated: Feb 9, 2026

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.9K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.9K
The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents
09:01

The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents

Published on: July 8, 2015

13.1K

Área de la Ciencia:

  • Robótica e Inteligencia Artificial
  • Aprendizaje Automático y Teoría de Control

Sus antecedentes:

  • El aprendizaje por refuerzo profundo (DRL) sobresale en procesos de decisión de Markov (MDP) totalmente observables.
  • La dinámica de rendimiento cambia en los procesos de decisión de Markov parcialmente observables (POMDP) debido a información de estado incompleta.
  • Los puntos de referencia DRL existentes a menudo se centran en los MDP, dejando el rendimiento de POMDP menos comprendido.

Objetivo del estudio:

  • Comparar empíricamente los algoritmos PPO, TD3 y SAC en variantes de POMDP de tareas de control continuo.
  • Investigar el impacto de la observabilidad parcial en el rendimiento relativo de los algoritmos DRL líderes.
  • Identificar adaptaciones algorítmicas que mejoren la robustez en entornos POMDP.

Principales métodos:

  • Análisis comparativo de Proximal Policy Optimization (PPO), Twin Delayed Deep Deterministic Policy Gradient (TD3) y Soft Actor-Critic (SAC).
  • Evaluación en formulaciones representativas de POMDP de puntos de referencia de control continuo estándar.
  • Introducción de bootstrapping de varios pasos a PPO y objetivos de varios pasos a TD3 (MTD3) y SAC (MSAC).

Principales resultados:

  • PPO demostró una robustez y un rendimiento superiores bajo observabilidad parcial, contrastando los resultados típicos de MDP.
  • TD3 y SAC mostraron una reducción del rendimiento en POMDPs en comparación con sus contrapartes de MDP.
  • TD3 modificado (MTD3) y SAC (MSAC) con objetivos de varios pasos exhibieron una mayor robustez en POMDPs.

Conclusiones:

  • La observabilidad parcial impacta significativamente el rendimiento del algoritmo DRL, invirtiendo las clasificaciones típicas.
  • El bootstrapping de varios pasos inherente de PPO proporciona una ventaja estabilizadora en POMDPs.
  • La adaptación de algoritmos como TD3 y SAC con objetivos de varios pasos ofrece un método práctico para mejorar su robustez en entornos parcialmente observables.