Reinforcement learning for suppression of collective activity in oscillatory ensembles
From MaRDI portal
Publication:5112985
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.
Recommendations
- Synchrony suppression in ensembles of coupled oscillators via adaptive vanishing feedback
- Synchronization via interacting reinforcement
- DELAYED FEEDBACK SUPPRESSION OF COLLECTIVE RHYTHMIC ACTIVITY IN A NEURONAL ENSEMBLE
- Control the collective behaviors in a functional neural network
- Collective dynamics of rate neurons for supervised learning in a reservoir computing system
- Controlling collective synchrony by feedback
- Learning through reinforcement and replicator dynamics
- Entrained collective rhythms of multicellular systems: partial impulsive control strategy
Cites work
- Chemical oscillations, waves, and turbulence
- Convolutional autoencoder and conditional random fields hybrid for predicting spatial-temporal chaos
- Desynchronizing double-pulse phase resetting and application to deep brain stimulation
- Dynamics of globally coupled oscillators: progress and perspectives
- Long-term anti-kindling effects of desynchronizing brain stimulation: a theoretical study
- MULTISITE COORDINATED DELAYED FEEDBACK FOR AN EFFECTIVE DESYNCHRONIZATION OF NEURONAL NETWORKS
- Phase resetting in medicine and biology. Stochastic modelling and data analysis
- Reinforcement learning. An introduction
- Synchrony suppression in ensembles of coupled oscillators via adaptive vanishing feedback
Cited in
(9)- Leveraging deep learning to control neural oscillators
- Controlling collective synchrony in oscillatory ensembles by precisely timed pulses
- Eliminating synchronization of coupled neurons adaptively by using feedback coupling with heterogeneous delays
- Control of chaos with time-delayed feedback based on deep reinforcement learning
- Data-driven control of oscillator networks with population-level measurement
- Desynchronizing oscillators coupled in multi-cluster networks through adaptively controlling partial networks
- Data-driven discovery of stochastic dynamical systems with \(\alpha\)-stable Lévy noise based on residual networks
- Optimizing charge-balanced pulse stimulation for desynchronization
- Taming chimeras in coupled oscillators using soft actor-critic based reinforcement learning
This page was built for publication: Reinforcement learning for suppression of collective activity in oscillatory ensembles
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5112985)
