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 Video

Updated: Nov 29, 2025

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients
06:11

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

Published on: April 18, 2025

1.2K

Task Learning Over Multi-Day Recording via Internally Rewarded Reinforcement Learning Based Brain Machine Interfaces.

Xiang Shen, Xiang Zhang, Yifan Huang

    IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
    |November 24, 2020
    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

    BIRC3 (Encoding Cellular Inhibitor of Apoptosis Protein 2) Variants Result in Dysregulated Receptor-Interacting Protein Kinase 1 Signaling Leading to Increased Epithelial Cell Death and Are Associated With Monogenic Crohn's Disease.

    Gastroenterology·2026
    Same author

    Reconfigurable on-chip polarizers enabled by phase-change-material-mediated loss engineering.

    Optics express·2026
    Same author

    A 'frost formation'-inspired near-infrared-responsive nitric oxide-releasing hydrogel for enhancing fat graft survival.

    Regenerative biomaterials·2026
    Same author

    Research on the Physiological Response Mechanism and Expression of Key Leaf Color Genes in 'Duojiao' Crabapple Under Partial Shading.

    Plants (Basel, Switzerland)·2026
    Same author

    Erratum: [Corrigendum] Proliferation, migration and invasion of triple negative breast cancer cells are suppressed by berbamine via the PI3K/Akt/MDM2/p53 and PI3K/Akt/mTOR signaling pathways.

    Oncology letters·2026
    Same author

    Dual-interface assembled silanized amide nanoclusters: driving light-carbon synergy to enhance photosynthesis in wheat.

    Journal of colloid and interface science·2026
    Same journal

    Ultrasound-Informed State Estimation of Wrist Tremor Dynamics via Koopman Operator for Personalized Sensory Peripheral Nerve Stimulation.

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
    Same journal

    Motion Intention Recognition and DDPG-Based Adaptive Impedance Control for a Robotic Upper-Limb Exoskeleton.

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
    Same journal

    CNN-Based Modelling Reveals Temporal Brain Dynamics of Auditory Intensity Processing.

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
    Same journal

    Pathology-Informed Augmentation Improves Cross-Cohort IMU-to-vGRF Estimation Between Healthy Adults and Adults With Osteoarthritis.

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
    Same journal

    Effects of task-driven head orientations on gait and balance during walking in virtual reality.

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
    Same journal

    Wearable sensor-based Mild Cognitive Impairment Identification: A Multi-Domain Gait Analysis Approach with Association Rule Mining.

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
    See all related articles

    This study introduces an internally rewarded brain-machine interface (BMI) using reinforcement learning (RL). The novel system autonomously learns new tasks by using internal brain signals as rewards, improving decoding accuracy and adaptability.

    Area of Science:

    • Neuroscience
    • Biomedical Engineering
    • Artificial Intelligence

    Background:

    • Autonomous brain-machine interfaces (BMIs) aim to restore function for paralyzed individuals.
    • Existing reinforcement learning (RL)-based decoders rely on external rewards and well-trained subjects, neglecting the intrinsic learning process.
    • The brain possesses internal mechanisms for reward-based learning that can be leveraged for autonomous BMI operation.

    Purpose of the Study:

    • To develop and demonstrate an internally rewarded RL-based BMI framework for autonomous task learning.
    • To utilize multi-site neural recordings and internal reward signals to enhance BMI decoder adaptability.
    • To investigate the BMI decoder's ability to adapt to non-stationary neural activity during task acquisition.

    Main Methods:

    More Related Videos

    A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents
    09:13

    A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

    Published on: May 3, 2012

    14.7K
    An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
    10:51

    An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

    Published on: March 10, 2011

    14.0K

    Related Experiment Videos

    Last Updated: Nov 29, 2025

    Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients
    06:11

    Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

    Published on: April 18, 2025

    1.2K
    A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents
    09:13

    A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

    Published on: May 3, 2012

    14.7K
    An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
    10:51

    An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

    Published on: March 10, 2011

    14.0K
    • Proposed an RL-based BMI framework incorporating internal reward signals derived from medial prefrontal cortex (mPFC) activity.
    • Used multi-site recordings from primary motor cortex (M1) and mPFC in rats learning a lever discrimination task.
    • Implemented a support vector machine (SVM) to classify reward vs. non-reward trials from mPFC activity, achieving 87.5% accuracy.
    • Replaced external water rewards with classified internal reward signals to update the BMI decoder.

    Main Results:

    • The internally rewarded BMI decoder demonstrated autonomous learning capabilities on a new task.
    • The system adapted to time-varying neural patterns during subject learning, showing asymptotic performance as behavioral learning progressed.
    • Multi-cortical recordings and internal critics improved decoding accuracy compared to traditional M1-only, externally guided decoders.
    • The SVM classifier accurately identified reward/non-reward trials, enabling effective internal reward signaling.

    Conclusions:

    • Internally rewarded RL-based BMIs show significant potential for autonomous task learning in new scenarios.
    • Leveraging internal reward signals can enhance BMI adaptability and performance, particularly in non-stationary neural environments.
    • This framework advances BMIs towards greater autonomy by mimicking the brain's natural learning processes.