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

Recovering Reward Functions From Distributed Expert Demonstrations via Bi-Level Maximum-Likelihood Optimization.

Guangyu Jiang, Shu Hong, Mahdi Imani

    IEEE Transactions on Neural Networks and Learning Systems
    |May 19, 2026
    PubMed
    Summary

    Federated maximum-likelihood IRL (F-ML-IRL) enables decentralized reward inference from expert data. This novel algorithm ensures convergence and outperforms centralized methods in robotic control tasks.

    Related Concept Videos

    Distributed Loads: Problem Solving01:21

    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

    <i>Capsicum annuum</i> RPW8 Confers Broad-Spectrum Resistance against Multiple Pathogens.

    Journal of agricultural and food chemistry·2026
    Same author

    Mechanisms of energy metabolism reprogramming and homeostasis maintenance in overwintering hibernating animals.

    Frontiers in veterinary science·2026
    Same author

    EtCBN-associated olfactory dysfunction involves Irf7 signaling and a microbiota-metabolite axis.

    Chemico-biological interactions·2026
    Same author

    Corrigendum to 'Quinoline yellow acts as a novel amyloid fibrillation probe by using surface-enhanced Raman spectroscopy' [Talanta 280 (2024) 126685].

    Talanta·2026
    Same author

    The crossroads between osteosarcopenia and intrinsic capacity-a narrative review.

    The journals of gerontology. Series A, Biological sciences and medical sciences·2026
    Same author

    Phase measurement deflectometry based on dual-frequency nonlinear fringes.

    Optics letters·2026

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Robotics

    Background:

    • Inverse reinforcement learning (IRL) infers reward functions and policies from expert demonstrations.
    • Current IRL methods often require centralized data access, posing challenges for decentralized and privacy-sensitive applications.

    Purpose of the Study:

    • To propose a novel federated maximum-likelihood IRL (F-ML-IRL) algorithm for decentralized reward inference.
    • To analyze the convergence rate of the proposed F-ML-IRL algorithm.

    Main Methods:

    • F-ML-IRL utilizes dual aggregation for global model updates.
    • Bi-level local updates optimize reward functions and agent policies using maximum likelihood and entropy regularization.

    Main Results:

    Related Experiment Videos

    • The F-ML-IRL algorithm's global model converges to a stationary point for reward and policy parameters in finite time.
    • Demonstrated convergence of recovered rewards in decentralized learning settings.
    • Outperformed centralized baselines in 12 out of 20 high-dimensional robotic control tasks.

    Conclusions:

    • F-ML-IRL effectively addresses the limitations of centralized IRL in decentralized environments.
    • The algorithm ensures convergence and achieves superior performance by leveraging distributed data.