Deep Reinforcement Learning using Cyclical Learning Rates

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.

Reinforcement Learning Approach to Vibration Compensation for Dynamic Feed Drive Systems

Vibration compensation is important for many domains. For the machine tool industry it translates to higher machining precision and longer component lifetime. Current methods for vibration damping have their shortcomings (e.g. need for accurate dynamic models). In this paper we present a reinforcement learning based approach to vibration compensation applied to a machine tool axis. The work describes the problem formulation, the solution, the implementation and experiments using industrial machine tool hardware and control system.