论文标题
使用周期性学习率深入的强化学习
Deep Reinforcement Learning using Cyclical Learning Rates
论文作者
论文摘要
深度强化学习（DRL）方法通常依赖于超参数的细致调整来成功解决问题。基于随机梯度下降（SGD）的优化程序中最有影响力的参数之一是学习率。我们研究了周期性学习，并提出了一种定义各种DRL问题的一般周期性学习率的方法。在本文中，我们提出了一种应用于复杂DRL问题的周期性学习方法。我们的实验表明，利用周期性学习取得了比高度调整的固定学习率相似甚至更好的结果。本文介绍了在DRL设置中首次应用周期性学习率的应用，这是克服手动超参数调整的一步。
Deep Reinforcement Learning (DRL) methods often rely on the meticulous tuning of hyperparameters to successfully resolve problems. One of the most influential parameters in optimization procedures based on stochastic gradient descent (SGD) is the learning rate. We investigate cyclical learning and propose a method for defining a general cyclical learning rate for various DRL problems. In this paper we present a method for cyclical learning applied to complex DRL problems. Our experiments show that, utilizing cyclical learning achieves similar or even better results than highly tuned fixed learning rates. This paper presents the first application of cyclical learning rates in DRL settings and is a step towards overcoming manual hyperparameter tuning.
