A Low Latency Adaptive Coding Spiking Framework for Deep Reinforcement Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Qin, Lang, Yan, Rui, Tang, Huajin
Formato: Preprint
Publicado: 2022
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917648078471168
author Qin, Lang
Yan, Rui
Tang, Huajin
author_facet Qin, Lang
Yan, Rui
Tang, Huajin
contents In recent years, spiking neural networks (SNNs) have been used in reinforcement learning (RL) due to their low power consumption and event-driven features. However, spiking reinforcement learning (SRL), which suffers from fixed coding methods, still faces the problems of high latency and poor versatility. In this paper, we use learnable matrix multiplication to encode and decode spikes, improving the flexibility of the coders and thus reducing latency. Meanwhile, we train the SNNs using the direct training method and use two different structures for online and offline RL algorithms, which gives our model a wider range of applications. Extensive experiments have revealed that our method achieves optimal performance with ultra-low latency (as low as 0.8% of other SRL methods) and excellent energy efficiency (up to 5X the DNNs) in different algorithms and different environments.
format Preprint
id arxiv_https___arxiv_org_abs_2211_11760
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle A Low Latency Adaptive Coding Spiking Framework for Deep Reinforcement Learning
Qin, Lang
Yan, Rui
Tang, Huajin
Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
In recent years, spiking neural networks (SNNs) have been used in reinforcement learning (RL) due to their low power consumption and event-driven features. However, spiking reinforcement learning (SRL), which suffers from fixed coding methods, still faces the problems of high latency and poor versatility. In this paper, we use learnable matrix multiplication to encode and decode spikes, improving the flexibility of the coders and thus reducing latency. Meanwhile, we train the SNNs using the direct training method and use two different structures for online and offline RL algorithms, which gives our model a wider range of applications. Extensive experiments have revealed that our method achieves optimal performance with ultra-low latency (as low as 0.8% of other SRL methods) and excellent energy efficiency (up to 5X the DNNs) in different algorithms and different environments.
title A Low Latency Adaptive Coding Spiking Framework for Deep Reinforcement Learning
topic Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
url https://arxiv.org/abs/2211.11760