logo
ResearchBunny Logo
Abstract
This paper proposes a brain-inspired spiking neural network (SNN)-based deep distributional reinforcement learning algorithm. It combines a bio-inspired multi-compartment neuron (MCN) model and a population coding method. The MCN model mimics the structure and function of biological neurons, while the population coding method implicitly represents quantile fractions in the spike information space. Experiments on Atari games show the model outperforms ANN-based FQF and ANN-SNN conversion methods.
Publisher
Not specified in provided text
Published On
Jan 18, 2023
Authors
Yinqian Sun, Yi Zeng, Feifei Zhao, Zhuoya Zhao
Tags
spiking neural networks
reinforcement learning
multi-compartment neuron
population coding
Atari games

Related Publications

Explore these studies to deepen your understanding of the subject.

Optical neural network via loose neuron array and functional learning
Engineering and Technology

Optical neural network via loose neuron array and functional learning

Y. Huo, H. Bao, et al.

Development and evaluation of deep learning algorithms for assessment of acute burns and the need for surgery
Medicine and Health

Development and evaluation of deep learning algorithms for assessment of acute burns and the need for surgery

C. Boissin, L. Laflamme, et al.

Design and Analysis of a Deep Learning Ensemble Framework Model for the Detection of COVID-19 and Pneumonia Using Large-Scale CT Scan and X-ray Image Datasets
Medicine and Health

Design and Analysis of a Deep Learning Ensemble Framework Model for the Detection of COVID-19 and Pneumonia Using Large-Scale CT Scan and X-ray Image Datasets

X. Xue, S. Chinnaperumal, et al.

Stretchable and anti-impact iontronic pressure sensor with an ultrabroad linear range for biophysical monitoring and deep learning-aided knee rehabilitation
Engineering and Technology

Stretchable and anti-impact iontronic pressure sensor with an ultrabroad linear range for biophysical monitoring and deep learning-aided knee rehabilitation

H. Xu, L. Gao, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs—just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny