CASIA OpenIR  > 复杂系统认知与决策实验室  > 听觉模型与认知计算
Multi-Scale Dynamic Coding Improved Spiking Actor Network for Reinforcement Learning
Zhang, Duzhen1,2; Zhang, Tielin1,2; Jia, Shuncheng1,2; Xu, Bo1,2,3
2022-06-28
Conference NameProceedings of the AAAI Conference on Artificial Intelligence (AAAI2022)
Conference DateFebruary 22–March 1, 2022
Conference PlaceOnline
Abstract

With the help of deep neural networks (DNNs), deep reinforcement learning (DRL) has achieved great success on many complex tasks, from games to robotic control. Compared to DNNs with partial brain-inspired structures and functions, spiking neural networks (SNNs) consider more biological features, including spiking neurons with complex dynamics and learning paradigms with biologically plausible plasticity principles. Inspired by the efficient computation of cell assembly in the biological brain, whereby memory-based coding is much more complex than readout, we propose a multiscale dynamic coding improved spiking actor network (MDC-SAN) for reinforcement learning to achieve effective decision-making. The population coding at the network scale is integrated with the dynamic neurons coding (containing 2nd-order neuronal dynamics) at the neuron scale towards a powerful spatial-temporal state representation. Extensive experimental results show that our MDC-SAN performs better than its counterpart deep actor network (based on DNNs) on four continuous control tasks from OpenAI gym. We think this is a significant attempt to improve SNNs from the perspective of efficient coding towards effective decision-making, just like that in biological networks.

Indexed ByEI
Language英语
IS Representative Paper
Sub direction classification类脑模型与计算
planning direction of the national heavy laboratory认知机理与类脑学习
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57352
Collection复杂系统认知与决策实验室_听觉模型与认知计算
Corresponding AuthorZhang, Tielin; Xu, Bo
Affiliation1.Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
3.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhang, Duzhen,Zhang, Tielin,Jia, Shuncheng,et al. Multi-Scale Dynamic Coding Improved Spiking Actor Network for Reinforcement Learning[C],2022.
Files in This Item: Download All
File Name/Size DocType Version Access License
19879-Article Text-2(2249KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Duzhen]'s Articles
[Zhang, Tielin]'s Articles
[Jia, Shuncheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Duzhen]'s Articles
[Zhang, Tielin]'s Articles
[Jia, Shuncheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Duzhen]'s Articles
[Zhang, Tielin]'s Articles
[Jia, Shuncheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 19879-Article Text-23892-1-2-20220628 (2).pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.