Reinforcement Learning for Planning Working Processes

One of the main purposes of the „Smart Virtual Worker“-project is the application of a digital human model for the simulation of industrial work tasks. This contribution focuses on the implementation of an autonomic action selection, such that a virtual agent is able to solve tasks under certain optimization criteria. To realize the autonomic action selection, we use the Q-Learning algorithm with different extensions. In this article, we describe these different learning algorithms and we briefly describe the performance of their implementation with regard to the industrial field.