Reinforcement learning for planning of a simulatedproduction line

Abstract: Deep reinforcement learning has been shown to be able to solve tasks without prior knowledge of thedynamics of the problems. In this thesis the applicability of reinforcement learning on the problem ofproduction planing is evaluated. Experiments are performed in order to reveal strengths and weak-nesses of the theory currently available. Reinforcement learning shows great potential but currentlyonly for a small class of problems. In order to use reinforcement learning to solve arbitrary or a largerclass of problems further work needs be done. This thesis was written at Syntronic Software Innova-tions.