Reinforcement learning for suppression of collective activity in oscillatory ensembles

Abstract

We present a use of modern data-based machine learning approaches to suppress self-sustained collective oscillations typically signaled by ensembles of degenerative neurons in the brain. The proposed hybrid model relies on two major components: an environment of oscillators and a policy-based reinforcement learning block. We report a model-agnostic synchrony control based on proximal policy optimization and two artificial neural networks in an Actor-Critic configuration. A class of physically meaningful reward functions enabling the suppression of collective oscillatory mode is proposed. The synchrony suppression is demonstrated for two models of neuronal populations -- for the ensembles of globally coupled limit-cycle Bonhoeffer-van der Pol oscillators and for the bursting Hindmarsh--Rose neurons.

arXiv comment8 pages, 8 figures

References in corpus (5)

• A Brief Survey of Deep Reinforcement Learning
• Sparse Identification of Nonlinear Dynamics for Rapid Model Recovery
• Deep learning algorithm for data-driven simulation of noisy dynamical system
• Synchrony suppression in ensembles of coupled oscillators via adaptive vanishing feedback
• Inferring the dynamics of oscillatory systems using recurrent neural networks

Cited by in corpus (4)

• Controlling collective synchrony in oscillatory ensembles by precisely timed pulses
• Reinforcement Learning Framework for Deep Brain Stimulation Study
• Inferring oscillator's phase and amplitude response from a scalar signal exploiting test stimulation
• Optimizing charge-balanced pulse stimulation for desynchronization