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

Specialization in multi-agent systems through learning

A Murciano1, J R Millán, J Zamora

  • 1Departamento de Biomatemática, Universidad Complutense de Madrid, Spain.

Biological Cybernetics
|May 1, 1997
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

Decontamination of environmental surfaces in hospitals to reduce hospital-acquired infections: a systematic review.

Infection prevention in practice·2026
Same author

Enhancing the evaporation rate of 3D solar evaporators by coating their surface with N-doped graphene and MnCoGe alloy compounds.

Journal of environmental management·2025
Same author

Human gut microbiota analysis of cystic fibrosis infants using metaproteomics.

Microbiology resource announcements·2024
Same author

Selection versus transmission: Quantitative and organismic biology in antibiotic resistance.

Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases·2024
Same author

Improvement in the management of suspected acute aortic syndrome in the emergency room through a clinical algorithm and study of predictive factors.

Radiologia·2023
Same author

Coronary computed tomography in emergencies: The importance of the radiologist's experience.

Radiologia·2023
Same journal

Harmonic memory in phasor neural networks.

Biological cybernetics·2026
Same journal

Correction: Decreased spinal inhibition leads to undiversified locomotor patterns.

Biological cybernetics·2026
Same journal

Foundational issues of network models in biology.

Biological cybernetics·2026
Same journal

Dynamical mechanisms for coordinating long-term working memory based on the precision of spike-timing in cortical neurons.

Biological cybernetics·2026
Same journal

Distinct dopaminergic spike-timing-dependent plasticity rules are suited to different functional roles.

Biological cybernetics·2026
Same journal

Fluctuation-response relations for a two-stage population of spiking neurons stimulated by common noise.

Biological cybernetics·2026
See all related articles

This study introduces a reinforcement learning method for specialization in artificial multi-agent systems. Homogeneous, non-communicating agents learn to specialize, improving team efficiency and task performance in dynamic environments.

Area of Science:

  • Artificial Intelligence
  • Multi-Agent Systems
  • Reinforcement Learning

Background:

  • Specialization enhances team fitness and resource acquisition in animal societies.
  • Artificial multi-agent systems offer a platform to study emergent specialization.
  • Homogeneous, non-communicating agents present unique challenges for cooperation.

Purpose of the Study:

  • To propose a reinforcement learning approach for emergent specialization in artificial multi-agent systems.
  • To enable homogeneous agents to learn specialized roles for efficient task completion.
  • To demonstrate scalability and adaptability in unknown, changing environments.

Main Methods:

  • A simple reinforcement learning algorithm was applied to a multi-agent system.
  • Agents started with identical functionalities and learned through interaction and reward.

Related Experiment Videos

  • The system was tasked with a complex gathering task without explicit communication channels.

    • Main Results:

    • Simulation experiments demonstrated successful specialization among homogeneous agents.
    • The multi-agent system achieved optimal or near-optimal performance on the gathering task.
    • The approach proved effective in unknown and dynamically changing environments.

    Conclusions:

    • Reinforcement learning can drive emergent specialization in non-communicating multi-agent systems.
    • Specialization leads to efficient cooperation and improved task performance.
    • The proposed method is scalable and robust to environmental uncertainties.