Bellman Memory Units: A neuromorphic framework for synaptic reinforcement learning with an evolving network topology

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Banerjee, Shreyan, Rounak, Aasifa, Pakrashi, Vikram
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911277323911168
author Banerjee, Shreyan
Rounak, Aasifa
Pakrashi, Vikram
author_facet Banerjee, Shreyan
Rounak, Aasifa
Pakrashi, Vikram
contents Application of neuromorphic edge devices for control is limited by the constraints on gradient-free online learning and scalability of the hardware across control problems. This paper introduces a synaptic Q-learning algorithm for the control of the classical Cartpole, where the Bellman equations are incorporated at the synaptic level. This formulation enables the iterative evolution of the network topology, represented as a directed graph, throughout the training process. This is followed by a similar approach called neuromorphic Bellman Memory Units (BMU(s)), which are implemented with the Neural Engineering Framework on Intel's Loihi neuromorphic chip. Topology evolution, in conjunction with mixed-signal computation, leverages the optimization of the number of neurons and synapses that could be used to design spike-based reinforcement learning accelerators. The proposed architecture can potentially reduce resource utilization on board, aiding the manufacturing of compact application-specific neuromorphic ICs. Moreover, the on-chip learning introduced in this work and implemented on a neuromorphic chip can enable adaptation to unseen control scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16066
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bellman Memory Units: A neuromorphic framework for synaptic reinforcement learning with an evolving network topology
Banerjee, Shreyan
Rounak, Aasifa
Pakrashi, Vikram
Systems and Control
Neural and Evolutionary Computing
Application of neuromorphic edge devices for control is limited by the constraints on gradient-free online learning and scalability of the hardware across control problems. This paper introduces a synaptic Q-learning algorithm for the control of the classical Cartpole, where the Bellman equations are incorporated at the synaptic level. This formulation enables the iterative evolution of the network topology, represented as a directed graph, throughout the training process. This is followed by a similar approach called neuromorphic Bellman Memory Units (BMU(s)), which are implemented with the Neural Engineering Framework on Intel's Loihi neuromorphic chip. Topology evolution, in conjunction with mixed-signal computation, leverages the optimization of the number of neurons and synapses that could be used to design spike-based reinforcement learning accelerators. The proposed architecture can potentially reduce resource utilization on board, aiding the manufacturing of compact application-specific neuromorphic ICs. Moreover, the on-chip learning introduced in this work and implemented on a neuromorphic chip can enable adaptation to unseen control scenarios.
title Bellman Memory Units: A neuromorphic framework for synaptic reinforcement learning with an evolving network topology
topic Systems and Control
Neural and Evolutionary Computing
url https://arxiv.org/abs/2511.16066