English

Noisy Spiking Actor Network for Exploration

Machine Learning 2025-12-12 v2 Neural and Evolutionary Computing

Abstract

As a general method for exploration in deep reinforcement learning (RL), NoisyNet can produce problem-specific exploration strategies. Spiking neural networks (SNNs), due to their binary firing mechanism, have strong robustness to noise, making it difficult to realize efficient exploration with local disturbances. To solve this exploration problem, we propose a noisy spiking actor network (NoisySAN) that introduces time-correlated noise during charging and transmission. Moreover, a noise reduction method is proposed to find a stable policy for the agent. Extensive experimental results demonstrate that our method outperforms the state-of-the-art performance on a wide range of continuous control tasks from OpenAI gym.

Keywords

Cite

@article{arxiv.2403.04162,
  title  = {Noisy Spiking Actor Network for Exploration},
  author = {Ding Chen and Peixi Peng and Tiejun Huang and Yonghong Tian},
  journal= {arXiv preprint arXiv:2403.04162},
  year   = {2025}
}

Comments

There are some issues with the method and it needs to be withdrawn

R2 v1 2026-06-28T15:11:44.279Z