Solving The Spike Feature Information Vanishing Problem In Spiking Deep Q Network With Potential Based Normalization
ASecurity**arXiv ID:** 2206.03654 **Authors:** Yinqian Sun, Yi Zeng, Yang Li **Published:** 2022-06-08T02:45:18Z **Abstract:** Brain inspired spiking neural networks (SNNs) have been successfully applied to many pattern recognition domains. The SNNs based deep structure have achieved considerable results in perceptual tasks, such as image classification, target detection. However, the application of deep SNNs in reinforcement learning (RL) tasks is still a problem to be explored. Although there have b...
- 3 stars
- 0 votes
- 0 copies
- 5 views
- Added September 11, 2026
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill solving-the-spike-feature-information-vanishing-problem-in-spiking-deep-q-network-with-potential-based-normalization --agent claude-codeAre you the author of Solving The Spike Feature Information Vanishing Problem In Spiking Deep Q Network With Potential Based Normalization?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-solving-the-spike-feature-information-vanishing-pr)# Solving the Spike Feature Information Vanishing Problem in Spiking Deep Q Network with Potential Based Normalization
**arXiv ID:** 2206.03654
**Authors:** Yinqian Sun, Yi Zeng, Yang Li
**Published:** 2022-06-08T02:45:18Z
**Abstract:**
Brain inspired spiking neural networks (SNNs) have been successfully applied to many pattern recognition domains. The SNNs based deep structure have achieved considerable results in perceptual tasks, such as image classification, target detection. However, the application of deep SNNs in reinforcement learning (RL) tasks is still a problem to be explored. Although there have been previous studies on the combination of SNNs and RL, most of them focus on robotic control problems with shallow networks or using ANN-SNN conversion method to implement spiking deep Q Network (SDQN). In this work, we mathematically analyzed the problem of the disappearance of spiking signal features in SDQN and proposed a potential based layer normalization(pbLN) method to directly train spiking deep Q networks. Experiment shows that compared with state-of-art ANN-SNN conversion method and other SDQN works, the proposed pbLN spiking deep Q networks (PL-SDQN) achieved better performance on Atari game tasks.
## Skill Description
This skill is generated from the arXiv paper: Solving the Spike Feature Information Vanishing Problem in Spiking Deep Q Network with Potential Based Normalization (2206.03654).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2206.03654](http://arxiv.org/abs/2206.03654v1)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.