论文标题
低潜伏期自适应编码尖峰框架，用于深入加固学习
A Low Latency Adaptive Coding Spiking Framework for Deep Reinforcement Learning
论文作者
论文摘要
近年来，由于其低功耗和事件驱动的功能，尖峰神经网络（SNN）已用于增强学习（RL）。但是，施加固定的编码方法的尖峰增强学习（SRL）仍然面临着高潜伏期和多功能性的问题。在本文中，我们使用可学习的矩阵乘法来编码和解码尖峰，改善编码器的灵活性，从而减少延迟。同时，我们使用直接培训方法训练SNN，并使用两个不同的结构进行在线和离线RL算法，这为我们的模型提供了更广泛的应用程序。广泛的实验表明，在不同算法和不同环境中，我们的方法具有超低潜伏期（低至其他SRL方法的0.8％）和出色的能源效率（最高5倍DNN）的最佳性能。
In recent years, spiking neural networks (SNNs) have been used in reinforcement learning (RL) due to their low power consumption and event-driven features. However, spiking reinforcement learning (SRL), which suffers from fixed coding methods, still faces the problems of high latency and poor versatility. In this paper, we use learnable matrix multiplication to encode and decode spikes, improving the flexibility of the coders and thus reducing latency. Meanwhile, we train the SNNs using the direct training method and use two different structures for online and offline RL algorithms, which gives our model a wider range of applications. Extensive experiments have revealed that our method achieves optimal performance with ultra-low latency (as low as 0.8% of other SRL methods) and excellent energy efficiency (up to 5X the DNNs) in different algorithms and different environments.
