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 Experiment Videos

Modular fuzzy-reinforcement learning approach with internal model capabilities for multiagent systems.

Mehmet Kaya1, Reda Alhajj

  • 1Department of Computer Engineering, Firat University, 23119 Elaziğ, Turkey. kaya@firat.edu.tr

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|September 21, 2004
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

RE-LIG: A Faithfulness-Driven Layer Integrated Gradients Framework for Explainable Medical Visual Question Answering.

Journal of imaging informatics in medicine·2026
Same author

A Hybrid Deep Learning Approach for Performance Prediction in Optical Communication Systems Based on PON Scenarios.

Sensors (Basel, Switzerland)·2026
Same author

Predictive machine learning models for rational permeability design in de novo macrocycle engineering: a review.

Journal of cheminformatics·2026
Same author

In-depth evaluation of biocompatibility of a porous titanium-zirconium binary alloy for potential bone implant.

Drug and chemical toxicology·2026
Same author

Pumpkin Seed Oil as a Candidate Intranasal Delivery Medium: Evidence From Nasal Epithelial Cell Culture.

The Journal of craniofacial surgery·2026
Same author

Scalable Unimodal and Multimodal Deep Learning for Multi-Label Chest Disease Detection: A Comparative Analysis.

Diagnostics (Basel, Switzerland)·2026

This study introduces a novel multiagent system architecture that enhances learning capabilities in complex environments. The fuzzy modular approach with internal models improves agent coordination and performance in multiagent learning.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Robotics

Background:

  • Multiagent systems face challenges with exponentially growing state spaces in complex learning problems.
  • Modeling other agents as part of the environment state is an unrealistic limitation in current approaches.
  • Existing methods often struggle to scale effectively with increasing numbers of agents.

Purpose of the Study:

  • To develop a novel multiagent system architecture that overcomes scalability issues in complex learning environments.
  • To integrate modularity, fuzzy logic, and internal models for improved agent learning and coordination.
  • To evaluate the effectiveness and robustness of the proposed architecture and learning approach.

Main Methods:

  • A fuzzy modular approach partitions the rule base into specialized modules for each agent.

Related Experiment Videos

  • Each module maps input fuzzy sets to action Q-values, defining agent state and action spaces.
  • Internal model tables are utilized within each module to predict the actions of other agents.
  • A parallel update method is integrated with the proposed architecture for efficient learning.

    • Main Results:

    • The proposed architecture demonstrates effectiveness in improving learning abilities within multiagent systems.
    • Experimental results show robust performance across different environments in a pursuit domain.
    • The integration of fuzzy logic and internal models successfully addresses state-space complexity.

    Conclusions:

    • The novel fuzzy modular architecture with internal models provides a scalable and effective solution for multiagent learning.
    • The approach enhances agent coordination and decision-making in complex, dynamic environments.
    • This research offers a significant advancement in the field of multiagent systems and artificial intelligence.