Noisy Spiking Actor Network for Exploration

arXiv:2403.04162v1 Announce Type: new
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 …

abstract actor arxiv binary cs.lg cs.ne exploration firing general making network networks neural networks noise reinforcement reinforcement learning robustness solve spiking neural networks strategies type