A differential Hebbian framework for biologically-plausible motor control

DOI10.1016/J.NEUNET.2022.03.002zbMATH Open1525.93121arXiv2006.13471OpenAlexW3212945014MaRDI QIDQ6072576FDOQ6072576

Authors: Sergio Verduzco-Flores, William Dorrell, Erik De Schutter 

Publication date: 13 October 2023

Published in: Neural Networks (Search for Journal in Brave)

Abstract: In this paper we explore a neural control architecture that is both biologically plausible, and capable of fully autonomous learning. It consists of feedback controllers that learn to achieve a desired state by selecting the errors that should drive them. This selection happens through a family of differential Hebbian learning rules that, through interaction with the environment, can learn to control systems where the error responds monotonically to the control signal. We next show that in a more general case, neural reinforcement learning can be coupled with a feedback controller to reduce errors that arise non-monotonically from the control signal. The use of feedback control can reduce the complexity of the reinforcement learning problem, because only a desired value must be learned, with the controller handling the details of how it is reached. This makes the function to be learned simpler, potentially allowing learning of more complex actions. We use simple examples to illustrate our approach, and discuss how it could be extended to hierarchical architectures.

Full work available at URL: https://arxiv.org/abs/2006.13471

Recommendations

• A hierarchical neural-network model for control and learning of voluntary movement
• Ideomotor feedback control in a recurrent neural network
• scientific article; zbMATH DE number 2099755
• scientific article; zbMATH DE number 1277117

zbMATH Keywords

feedback controlsynaptic plasticityreinforcement learningmotor control

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Feedback control (93B52) Linear systems in control theory (93C05) Multivariable systems, multidimensional control systems (93C35)

Cites Work

• Title not available (Why is that?)
• NEURAL EXCITABILITY, SPIKING AND BURSTING
• A control design method for a class of switched linear systems
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Reinforcement learning. An introduction
• Forward models for physiological motor control
• ISO Learning Approximates a Solution to the Inverse-Controller Problem in an Unsupervised Behavioral Paradigm
• Strongly Improved Stability and Faster Convergence of Temporal Sequence Learning by Using Input Correlations Only
• Wavelet transforms versus Fourier transforms
• Learning Curves for Stochastic Gradient Descent in Linear Feedforward Networks
• Mathematical properties of neuronal TD-rules and differential Hebbian learning: a comparison
• MOSAIC for multiple-reward environments
• A stable added-mass partitioned (AMP) algorithm for elastic solids and incompressible flow
• Sensitivity Derivatives for Flexible Sensorimotor Learning
• On the Asymptotic Equivalence Between Differential Hebbian and Temporal Difference Learning

Cited In (1)

• A model for the transfer of control from the brain to the spinal cord through synaptic learning

This page was built for publication: A differential Hebbian framework for biologically-plausible motor control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6072576)