Jove
Visualize
Contact Us

Related Concept Videos

Reinforcement01:23

Reinforcement

739
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:
739
Observational Learning01:12

Observational Learning

744
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...
744
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

334
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
334
Reinforcement Schedules01:24

Reinforcement Schedules

391
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,...
391
Open and closed-loop control systems01:17

Open and closed-loop control systems

1.5K
Control systems are foundational elements in automation and engineering. They are broadly categorized into open-loop and closed-loop systems. These classifications hinge on the presence or absence of feedback mechanisms, significantly influencing the system's performance, complexity, and application.
An open-loop control system operates without feedback from the output. It consists of two primary elements: the controller and the controlled process. The controller receives an input signal...
1.5K
Control Systems: Applications01:25

Control Systems: Applications

1.0K
Electrical engineering plays a pivotal role in our daily lives, with control systems at the heart of many applications, from home appliances to sophisticated space shuttles. Control systems manage and regulate the behavior of devices and processes, ensuring they function safely, correctly, and efficiently.
In modern vehicles, control systems manage various functions to enhance performance and safety. The steering wheel and accelerator are primary inputs in a car's control system. The...
1.0K

You might also read

Related Articles

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

Sort by
Same author

Automated Measurements of Tooth Size and Arch Widths on Cone-Beam Computerized Tomography and Scan Images of Plaster Dental Models.

Bioengineering (Basel, Switzerland)·2025
Same author

Contagious infection-free medical interaction system with machine vision controlled by remote hand gesture during an operation.

Computational and structural biotechnology journal·2024
Same author

Strangeness-driven exploration in multi-agent reinforcement learning.

Neural networks : the official journal of the International Neural Network Society·2024
Same author

Novel Procedure for Automatic Registration between Cone-Beam Computed Tomography and Intraoral Scan Data Supported with 3D Segmentation.

Bioengineering (Basel, Switzerland)·2023
Same author

Intelligent Task Dispatching and Scheduling Using a Deep Q-Network in a Cluster Edge Computing System.

Sensors (Basel, Switzerland)·2022
Same author

Compound Context-Aware Bayesian Inference Scheme for Smart IoT Environment.

Sensors (Basel, Switzerland)·2022
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Dec 27, 2025

A Fully Automated Rodent Conditioning Protocol for Sensorimotor Integration and Cognitive Control Experiments
09:43

A Fully Automated Rodent Conditioning Protocol for Sensorimotor Integration and Cognitive Control Experiments

Published on: April 15, 2014

10.9K

Federated Reinforcement Learning for Training Control Policies on Multiple IoT Devices.

Hyun-Kyo Lim1, Ju-Bong Kim2, Joo-Seong Heo1

  • 1Department of Interdisciplinary Program in Creative Engineering, Korea University of Technology and Education, Cheonan 31253, Korea.

Sensors (Basel, Switzerland)
|March 4, 2020
PubMed
Summary
This summary is machine-generated.

Federated reinforcement learning enables multiple IoT devices to share learning experiences, accelerating policy optimization. This collaborative approach enhances control for diverse IoT devices, improving learning speed with more agents.

Keywords:
Actor–Critic PPOfederated reinforcement learningmulti-device control

More Related Videos

A Flexible Platform for Monitoring Cerebellum-Dependent Sensory Associative Learning
11:32

A Flexible Platform for Monitoring Cerebellum-Dependent Sensory Associative Learning

Published on: January 19, 2022

3.8K

Related Experiment Videos

Last Updated: Dec 27, 2025

A Fully Automated Rodent Conditioning Protocol for Sensorimotor Integration and Cognitive Control Experiments
09:43

A Fully Automated Rodent Conditioning Protocol for Sensorimotor Integration and Cognitive Control Experiments

Published on: April 15, 2014

10.9K
A Flexible Platform for Monitoring Cerebellum-Dependent Sensory Associative Learning
11:32

A Flexible Platform for Monitoring Cerebellum-Dependent Sensory Associative Learning

Published on: January 19, 2022

3.8K

Area of Science:

  • Artificial Intelligence
  • Internet of Things (IoT)
  • Machine Learning

Background:

  • Reinforcement learning (RL) is increasingly applied to optimize Internet of Things (IoT) device control.
  • Individual RL agents trained on single IoT devices may not generalize well to devices with slightly different dynamics.
  • Independent RL training for each IoT device is often resource-intensive and time-consuming.

Purpose of the Study:

  • To develop a novel federated reinforcement learning (FRL) architecture for multi-agent IoT systems.
  • To enable agents controlling similar IoT devices with varying dynamics to collaboratively learn optimal control policies.
  • To accelerate the learning process and improve policy generalization across multiple IoT devices.

Main Methods:

  • Proposed a federated reinforcement learning architecture enabling agents to share learning experiences (loss function gradients) and mature policy parameters.
  • Integrated the Actor-Critic Proximal Policy Optimization (Actor-Critic PPO) algorithm within each agent.
  • Developed an efficient procedure for gradient sharing and model parameter transfer among agents.

Main Results:

  • Demonstrated that the proposed FRL scheme effectively facilitates the learning process for multiple IoT devices.
  • Showcased that the learning speed is enhanced when more agents participate in the federated learning process.
  • Validated the approach using multiple rotary inverted pendulum devices.

Conclusions:

  • Federated reinforcement learning offers an efficient solution for optimizing control policies in multi-agent IoT environments with heterogeneous dynamics.
  • Collaborative learning through experience and parameter sharing significantly accelerates policy acquisition.
  • The proposed FRL architecture improves learning efficiency and scalability in IoT applications.