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,...

Reinforcement

Reinforcement

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:

Sequence Networks of Rotating Machines

Sequence Networks of Rotating Machines

A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...

Distributed Loads: Problem Solving

Distributed Loads: Problem Solving

Beams are structural elements commonly employed in engineering applications requiring different load-carrying capacities. The first step in analyzing a beam under a distributed load is to simplify the problem by dividing the load into smaller regions, which allows one to consider each region separately and calculate the magnitude of the equivalent resultant load acting on each portion of the beam. The magnitude of the equivalent resultant load for each region can be determined by calculating...

You might also read

Related Articles

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

Sort by

Same author

Employing an immunoinformatics approach revealed potent multi-epitope based subunit vaccine for lymphocytic choriomeningitis virus.

Journal of infection and public health·2023

Same author

Microbial-induced calcium carbonate precipitation: Influencing factors, nucleation pathways, and application in waste water remediation.

The Science of the total environment·2022

Same author

Synergistic removal of nitrate by a cellulose-degrading and denitrifying strain through iron loaded corn cobs filled biofilm reactor at low C/N ratio: Capability, enhancement and microbiome analysis.

Bioresource technology·2022

Same author

Ring Expansion of Isatins <i>via</i> 1,2-Phospha-Brook Rearrangement: A Route to the Synthesis of 2-Quinolinone-Derived <i>p</i>-Quinone Methides.

The Journal of organic chemistry·2022

Same author

Production of a recyclable nanobiocatalyst to synthesize quinazolinone derivatives.

RSC advances·2022

Same author

Comparative Pan-Genomic Analysis Revealed an Improved Multi-Locus Sequence Typing Scheme for <i>Staphylococcus aureus</i>.

Genes·2022

Search research articles

Related Experiment Videos

Distributed MAC scheduling in IEEE 802.15.7-oriented VLC networks via federated deep reinforcement learning.

Iván Sánchez Salazar¹, Pablo Palacios Játiva², María Camila Reyes²

¹Department of Networking and Telecommunication Engineering, Universidad de Las Américas, Quito, Ecuador. ivan.sanchez.salazar@udla.edu.ec.

Scientific Reports

|July 7, 2026

Summary

This study introduces a federated deep reinforcement learning framework for visible light communication (VLC) networks, significantly reducing packet latency and improving reliability. The novel approach enhances scheduling efficiency in dense, multi-luminaire VLC systems.

Related Experiment Videos

Area of Science:

Wireless Communication
Artificial Intelligence
Network Engineering

Background:

Visible Light Communication (VLC) networks face challenges in dense deployments due to interference, blockage, and noise.
Existing fixed Medium Access Control (MAC) policies are insufficient for dynamic VLC environments.
The IEEE 802.15.7 standard provides a basis for VLC PHY/MAC layers, but requires adaptive scheduling.

Purpose of the Study:

To develop a distributed MAC scheduling framework for multi-luminaire VLC networks using federated deep reinforcement learning.
To enhance scheduling policies by enabling luminaires to learn and adapt to dynamic network conditions.
To improve the performance and reliability of VLC networks while maintaining lighting feasibility.

Main Methods:

A federated deep reinforcement learning framework was designed, where each luminaire acts as a local scheduling agent.
Luminaires exchange model parameters, not raw data, with a central server for coordinated policy updates, preserving data locality.
A discrete-time simulator modeled a multi-luminaire indoor VLC scenario with various performance-impacting factors.

Main Results:

The proposed scheduler reduced average packet latency from 45 ms to 31 ms and 95th-percentile latency from 92 ms to 66 ms compared to a centralized DQN baseline.
Packet delivery ratio improved from 0.858 to 0.902 under blockage, and packet error rate decreased under high ambient light.
The method achieved high fairness (Jain index of 0.96), reduced synchronization overhead, and faster convergence, while satisfying illumination constraints.

Conclusions:

Federated deep reinforcement learning offers an effective distributed MAC scheduling solution for dense VLC networks.
Periodic federated parameter sharing balances performance gains with data locality and reduced coordination costs.
The framework demonstrates improved reliability, fairness, and scalability in VLC systems, meeting lighting feasibility requirements.