Deep Reinforcement Learning using Cyclical Learning Rates
This work addresses hyperparameter tuning challenges for deep reinforcement learning practitioners, but it is incremental as it adapts an existing technique to a new domain.
The paper tackles the problem of manual hyperparameter tuning in deep reinforcement learning by proposing a cyclical learning rate method, achieving similar or better results than highly tuned fixed learning rates in experiments.
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.