Search research 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

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

Impact of modified ERAS protocol implementation on length of stay and complications in elderly hip fracture patients: a before-and-after study.

European journal of trauma and emergency surgery : official publication of the European Trauma Society·2026

Same author

Clinical Probation Teaching in Undergraduate Implant Dentistry Course: Online Versus Offline Modes.

European journal of dental education : official journal of the Association for Dental Education in Europe·2026

Same author

STAT3 Inhibitor Suppresses CCL2-dependent Recruitment and M2 Polarization of Tumor-associated Macrophages to Enhance Antitumor Immunity in Ovarian Cancer.

Applied biochemistry and biotechnology·2026

Same author

Association of serum vitamin D and serum vitamin C with the risk of melanoma among adults in the United States: a cross-sectional analysis of 2003-2006 and 2017-2018 NHANES data.

Journal of clinical biochemistry and nutrition·2026

Same author

Triple-interlocked-nanotwinned bulk magnesium alloys with exceptional strength and ageing resistance.

Nature communications·2026

Same author

Screening and evaluation of potential histone deacetylase inhibitors against Babesia infections.

International journal for parasitology. Drugs and drug resistance·2026

Same journal

DARUMA: a gateway to fast and easy prediction of intrinsically disordered regions.

PeerJ. Computer science·2026

Same journal

Alzheimer's disease detection using a quantum deep neural network with Haralick feature extraction and simulated annealing optimization.

PeerJ. Computer science·2026

Same journal

Network anomaly detection using Deep Autoencoder and parallel Artificial Bee Colony algorithm-trained neural network.

PeerJ. Computer science·2026

Same journal

An anomaly detection model for multivariate time series with anomaly perception.

PeerJ. Computer science·2026

Same journal

Retraction: A wormhole attack detection method for tactical wireless sensor networks.

PeerJ. Computer science·2026

Same journal

Evaluation of mental disorder with prioritization of its type by utilizing the bipolar complex fuzzy decision-making approach based on Schweizer-Sklar prioritized aggregation operators.

PeerJ. Computer science·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 21, 2025

Movement Retraining using Real-time Feedback of Performance

Movement Retraining using Real-time Feedback of Performance

Published on: January 17, 2013

Deep reinforcement learning task scheduling method based on server real-time performance.

Jinming Wang¹, Shaobo Li¹, Xingxing Zhang¹

¹State Key Laboratory of Public Big Data, Guizhou University, Guiyang, Guizhou, China.

Peerj. Computer Science

|July 10, 2024

Summary

This summary is machine-generated.

This study introduces a novel deep reinforcement learning task scheduling method (SRP-DRL) that considers real-time server performance, not just load. SRP-DRL optimizes cloud task scheduling, improving efficiency and user experience by reducing response times and load variance.

Keywords:

Cloud task scheduling Deep reinforcement learning Load and performance Load balancing State augmentation

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

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

Published on: August 26, 2018

Related Experiment Videos

Last Updated: Jun 21, 2025

Movement Retraining using Real-time Feedback of Performance

Movement Retraining using Real-time Feedback of Performance

Published on: January 17, 2013

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

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

Published on: August 26, 2018

Area of Science:

Cloud Computing
Artificial Intelligence
Performance Optimization

Background:

Cloud task scheduling is hindered by traditional methods ignoring real-time server load-performance dynamics.
This leads to inaccurate processing capability assessment, impacting efficiency and user experience.

Purpose of the Study:

To develop an advanced task scheduling method for cloud environments.
To improve cloud task scheduling efficiency, performance, and user experience by incorporating real-time server performance.

Main Methods:

Constructed a performance platform model to monitor server real-time load and performance.
Proposed a deep reinforcement learning task scheduling method based on server real-time performance (SRP-DRL).
Integrated a real-time performance-aware strategy into the deep reinforcement learning (DRL) model.

Main Results:

SRP-DRL demonstrated superior performance over traditional methods (Random, Round-Robin, EITF, BEST-FIT).
Achieved better task average response time, success rate, and server average load variance.
Significantly reduced server average load variance during high task arrival rates.

Conclusions:

The SRP-DRL method effectively optimizes cloud system performance under latency constraints.
Real-time performance-aware scheduling enhances DRL model perception and load-balancing capabilities.
SRP-DRL offers a significant improvement for efficient cloud task management.