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

Reinforcement learning for a biped robot based on a CPG-actor-critic method.

Yutaka Nakamura1, Takeshi Mori, Masa-aki Sato

  • 1Nara Institute of Science and Technology, 8916-5 Takayama-cho, Ikoma, Nara 630-0192, Japan. nakamura@ams.eng.osaka-u.ac.jp

Neural Networks : the Official Journal of the International Neural Network Society
|April 7, 2007
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

Template-Based Label Propagation for Mouse Brain MRI Skull Stripping.

Neuroinformatics·2026
Same author

CRTC1 knockdown in the marmoset visual cortex induces neuronal IEG overexpression, HFOs, and neurodegeneration.

Neuroscience research·2026
Same author

Brain/MINDS Marmoset Brain Atlas 2.0: Population Cortical Parcellation With Multi-Modal Templates.

Scientific data·2026
Same author

Blaming luck, claiming skill: Self-attribution bias in error assignment.

PLoS computational biology·2025
Same author

Decoding Confidence in Future Event: EEG Markers of Prospective Confidence in Perceptual and Memory Tasks.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Neural mechanisms of individual differences in prior weight during scene recognition.

NeuroImage·2025
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

We developed a novel reinforcement learning method, CPG-actor-critic, to enable central pattern generators (CPGs) to autonomously learn rhythmic movements. This method successfully trained a biped robot to walk stably and adapt to environmental changes.

Area of Science:

  • Robotics
  • Computational Neuroscience
  • Artificial Intelligence

Background:

  • Central Pattern Generators (CPGs) are neural circuits responsible for rhythmic movements like locomotion in animals.
  • Existing research focuses on understanding and replicating CPG-controlled rhythmic movements.
  • Autonomous control of CPGs remains a challenge.

Purpose of the Study:

  • To propose a novel reinforcement learning framework for autonomous CPG controller learning.
  • To introduce an improved actor-critic architecture for CPG training.
  • To demonstrate the method's efficacy in controlling a biped robot.

Main Methods:

  • Developed the "CPG-actor-critic" method, a reinforcement learning framework.
  • Introduced a new actor architecture within the CPG controller.

Related Experiment Videos

  • Utilized a stochastic policy gradient algorithm for training.

    • Main Results:

    • Successfully trained the CPG controller for a biped robot using the proposed method.
    • The biped robot achieved stable walking capabilities.
    • The robot demonstrated adaptability to environmental changes.

    Conclusions:

    • The CPG-actor-critic method enables autonomous learning of CPG controllers.
    • This approach facilitates stable and adaptive locomotion in robotic systems.
    • The findings have implications for bio-inspired robotics and control systems.