Towards a Pittsburgh-style LCS for learning manufacturing machinery parametrizations
Michael Heider, David Pätzel, Jörg Hähner · 2020
We present a first evaluation of a new accuracy-based Pittsburgh-style learning classifier system (LCS) for supervised learning of multi-dimensional continuous decision problems: The SupRB-1 (Supervised Rule-Based) learning system. Designed primarily for finding parametrizations for industrial machinery, SupRB-1 learns an approximation of a continuous quality function from examples (consisting of situations, choices and associated qualities---all continous, the first two possibly multi-dimensional) and is then able to make an optimal choice as well as predict the quality of a choice in a given situation. This paper shows and discusses preliminary results of SupRB-1's performance on an additive manufacturing problem.