Jove
Visualize
Contact Us
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 Concept Videos

Reinforcement01:23

Reinforcement

984
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:
984
Collisions in Multiple Dimensions: Problem Solving01:06

Collisions in Multiple Dimensions: Problem Solving

5.5K
In multiple dimensions, the conservation of momentum applies in each direction independently. Hence, to solve collisions in multiple dimensions, we should write down the momentum conservation in each direction separately. To help understand collisions in multiple dimensions, consider an example.
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...
5.5K
Observational Learning01:12

Observational Learning

1.1K
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...
1.1K
Reinforcement Schedules01:24

Reinforcement Schedules

547
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,...
547
Associative Learning01:27

Associative Learning

1.5K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
1.5K
Collisions in Multiple Dimensions: Introduction01:05

Collisions in Multiple Dimensions: Introduction

7.1K
It is far more common for collisions to occur in two dimensions; that is, the initial velocity vectors are neither parallel nor antiparallel to each other. Let's see what complications arise from this. The first idea is that momentum is a vector. Like all vectors, it can be expressed as a sum of perpendicular components (usually, though not always, an x-component and a y-component, and a z-component if necessary). Thus, when the statement of conservation of momentum is written for a...
7.1K

You might also read

Related Articles

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

Sort by
Same author

A Policy-Guided Reinforcement Learning Method for Encirclement Control in Multiobstacle Environment.

IEEE transactions on neural networks and learning systems·2025
Same author

An Adaptive Filter for Nonlinear Multi-Sensor Systems with Heavy-Tailed Noise.

Sensors (Basel, Switzerland)·2020
Same author

Monotonic regression: a new way for correlating subjective and objective ratings in image quality research.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2011
Same author

Enhancing the convergence efficiency of a self-propelled agent system via a weighted model.

Physical review. E, Statistical, nonlinear, and soft matter physics·2010

Related Experiment Videos

A graph-based safe reinforcement learning method for multi-agent cooperation.

Fandi Gou1, Haikuo Du1, Yunze Cai2

  • 1School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, 200240, China.

Neural Networks : the Official Journal of the International Neural Network Society
|February 20, 2026
PubMed
Summary

This study introduces Graph-based Safe Multi-Agent Reinforcement Learning (GS-MARL) to improve safety and scalability in multi-agent systems. GS-MARL enhances performance in communication-limited scenarios, achieving higher success rates than existing methods.

Keywords:
Collision avoidanceConstrained policy optimizationGraph neural networksMulti-agent cooperationSafe reinforcement learning

Related Experiment Videos

Area of Science:

  • Artificial Intelligence
  • Robotics
  • Control Systems

Background:

  • Multi-Agent Systems (MAS) face challenges in safety and communication.
  • Existing Multi-Agent Reinforcement Learning (MARL) methods struggle with safety and scalability due to reward shaping and fully connected communication.

Purpose of the Study:

  • To propose a novel framework, Graph-based Safe MARL (GS-MARL), enhancing safety and scalability in MAS.
  • To address limitations of current MARL algorithms in practical applications.

Main Methods:

  • Utilizing the inherent graph structure of MAS with a Graph Neural Network (GNN) for message passing.
  • Implementing a constrained joint policy optimization method for improved safety under local observations.

Main Results:

  • GS-MARL demonstrates a superior trade-off between optimality and safety compared to existing methods.
  • Achieved at least a 10% higher success rate in large-scale, communication-limited scenarios.
  • Validated through simulation experiments and hardware implementation with Mecanum-wheeled vehicles.

Conclusions:

  • GS-MARL effectively enhances safety and scalability in MARL.
  • The framework is practical for real-world applications, including robotic systems.