Search research articles

Related Concept Videos

Reinforcement Schedules

Reinforcement Schedules

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,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Bayesian Topology Inference of Regulatory Networks under Partial Observability.

Results in control and optimization·2026

Same author

BoolFilter: an R package for estimation and identification of partially-observed Boolean dynamical systems.

BMC bioinformatics·2017

Same journal

Covid-19 Diagnosis by WE-SAJ.

Systems science & control engineering·2022

Same journal

Heart rate control using first- and second-order models during treadmill exercise.

Systems science & control engineering·2021

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 27, 2025

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Deep Reinforcement Learning Sensor Scheduling for Effective Monitoring of Dynamical Systems.

Mohammad Alali¹, Armita Kazeminajafabadi¹, Mahdi Imani¹

¹Northeastern University, 360 Huntington Ave, Boston, MA, 02115, U.S.

Systems Science & Control Engineering

|April 29, 2024

Summary

This summary is machine-generated.

This study introduces a novel reinforcement learning approach for optimal sensor scheduling in complex systems. It addresses limitations of greedy methods by considering long-term impacts for better real-time monitoring.

Keywords:

Hidden Markov Models Monitoring Reinforcement Learning Sensor Scheduling State Estimation

More Related Videos

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

Published on: May 16, 2025

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Published on: May 8, 2021

Related Experiment Videos

Last Updated: Jun 27, 2025

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

Published on: May 16, 2025

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Published on: May 8, 2021

Area of Science:

Systems Engineering
Control Theory
Machine Learning

Background:

Technological advancements allow diverse sensor modalities for system monitoring.
Resource and computational constraints limit real-time processing of sensor data in complex systems.
Effective sensor scheduling is crucial for optimizing monitoring objectives under limitations.

Purpose of the Study:

To develop an optimal sensor scheduling method for systems modeled by hidden Markov models.
To overcome the limitations of existing greedy sensor selection/scheduling approaches.
To propose a method that considers the long-term impact of sensor choices on monitoring goals.

Main Methods:

Formulated optimal sensor scheduling as a reinforcement learning problem.
Defined the problem over the posterior distribution of system states.
Derived a deep reinforcement learning policy for offline learning and real-time execution.

Main Results:

The proposed deep reinforcement learning policy enables effective sensor scheduling.
The method is applicable to various monitoring objectives expressible via posterior state distributions.
Demonstrated accuracy and robustness in monitoring networked system security and gene regulatory networks.

Conclusions:

The developed deep reinforcement learning approach provides a robust solution for sensor scheduling.
This method offers a significant improvement over traditional greedy techniques.
The approach is versatile and applicable to diverse complex system monitoring tasks.