Deep Reinforcement Learning with Spiking Q-learning

arXiv:2201.09754v2 Announce Type: replace-cross
Abstract: 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 (RL). There are only a few existing SNN-based RL methods at present. Most of them either lack generalization ability or employ Artificial Neural Networks (ANNs) to estimate value function in training. The former needs to tune …

abstract artificial artificial intelligence arxiv consumption control cs.ai cs.lg cs.ne energy hardware intelligence networks neural networks neuromorphic q-learning reinforcement reinforcement learning snn spiking neural networks tasks type