清晨好,您是今天最早来到科研通的研友!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您科研之路漫漫前行!

Fully Spiking Actor Network With Intralayer Connections for Reinforcement Learning

尖峰神经网络 神经形态工程学 强化学习 计算机科学 人口 人工智能 任务(项目管理) 领域(数学分析) 学习规律 维数(图论) 人工神经网络 工程类 数学分析 人口学 数学 系统工程 社会学 纯数学
作者
Ding Chen,Peixi Peng,Tiejun Huang,Yonghong Tian
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:: 1-13
标识
DOI:10.1109/tnnls.2024.3352653
摘要

With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a promising energy-efficient way for realistic control tasks by combining SNNs with deep reinforcement learning (DRL). In this article, we focus on the task where the agent needs to learn multidimensional deterministic policies to control, which is very common in real scenarios. Recently, the surrogate gradient method has been utilized for training multilayer SNNs, which allows SNNs to achieve comparable performance with the corresponding deep networks in this task. Most existing spike-based reinforcement learning (RL) methods take the firing rate as the output of SNNs, and convert it to represent continuous action space (i.e., the deterministic policy) through a fully connected (FC) layer. However, the decimal characteristic of the firing rate brings the floating-point matrix operations to the FC layer, making the whole SNN unable to deploy on the neuromorphic hardware directly. To develop a fully spiking actor network (SAN) without any floating-point matrix operations, we draw inspiration from the nonspiking interneurons found in insects and employ the membrane voltage of the nonspiking neurons to represent the action. Before the nonspiking neurons, multiple population neurons are introduced to decode different dimensions of actions. Since each population is used to decode a dimension of action, we argue that the neurons in each population should be connected in time domain and space domain. Hence, the intralayer connections are used in output populations to enhance the representation capacity. This mechanism exists extensively in animals and has been demonstrated effectively. Finally, we propose a fully SAN with intralayer connections (ILC-SAN). Extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art performance on continuous control tasks from OpenAI gym. Moreover, we estimate the theoretical energy consumption when deploying ILC-SAN on neuromorphic chips to illustrate its high energy efficiency.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
3120221053完成签到,获得积分10
14秒前
是玥玥啊完成签到 ,获得积分10
14秒前
小新小新完成签到 ,获得积分10
19秒前
Qvby3完成签到 ,获得积分10
26秒前
英姑应助ceeray23采纳,获得20
35秒前
imica完成签到 ,获得积分10
50秒前
bkagyin应助ceeray23采纳,获得20
1分钟前
Ralph完成签到,获得积分10
1分钟前
科研搬运工完成签到,获得积分0
1分钟前
binbinbin发布了新的文献求助20
1分钟前
binbinbin完成签到,获得积分20
1分钟前
cy完成签到,获得积分10
2分钟前
满意的伊完成签到,获得积分10
2分钟前
2分钟前
John完成签到 ,获得积分10
2分钟前
蔡从安完成签到,获得积分20
2分钟前
傲娇而又骄傲完成签到 ,获得积分10
3分钟前
精明晓刚发布了新的文献求助10
3分钟前
星辰大海应助精明晓刚采纳,获得10
3分钟前
Joeswith完成签到,获得积分10
3分钟前
优美的明辉完成签到 ,获得积分10
3分钟前
帅气的沧海完成签到 ,获得积分10
4分钟前
jlwang完成签到,获得积分10
4分钟前
4分钟前
彦嘉发布了新的文献求助10
4分钟前
宇文雨文完成签到 ,获得积分10
4分钟前
4分钟前
末末完成签到 ,获得积分10
5分钟前
5分钟前
ceeray23发布了新的文献求助20
5分钟前
科研通AI2S应助科研通管家采纳,获得10
5分钟前
笨笨完成签到 ,获得积分10
5分钟前
芒芒发paper完成签到 ,获得积分10
5分钟前
顺心蜜粉发布了新的文献求助30
5分钟前
顺心蜜粉完成签到,获得积分10
6分钟前
6分钟前
CC发布了新的文献求助10
6分钟前
淞淞于我完成签到 ,获得积分10
6分钟前
Jenny发布了新的文献求助50
6分钟前
CC完成签到,获得积分10
6分钟前
高分求助中
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3990568
求助须知:如何正确求助?哪些是违规求助? 3532220
关于积分的说明 11256532
捐赠科研通 3271057
什么是DOI,文献DOI怎么找? 1805207
邀请新用户注册赠送积分活动 882302
科研通“疑难数据库(出版商)”最低求助积分说明 809234