Multiobjective Reinforcement Learning for Reconfigurable Adaptive Optimal Control of Manufacturing Processes

TL;DR

This paper introduces a novel model-free multiobjective reinforcement learning method for adaptive optimal control in manufacturing, effectively handling changing objectives and unknown weights in dynamic production environments.

Contribution

It presents a new reinforcement learning approach that adapts to changing objectives without prior knowledge of their importance, improving manufacturing process control.

Findings

Sample-efficient learning in control configurations

Handles changing objective weights effectively

Applicable to real-world manufacturing scenarios

Abstract

In industrial applications of adaptive optimal control often multiple contrary objectives have to be considered. The weights (relative importance) of the objectives are often not known during the design of the control and can change with changing production conditions and requirements. In this work a novel model-free multiobjective reinforcement learning approach for adaptive optimal control of manufacturing processes is proposed. The approach enables sample-efficient learning in sequences of control configurations, given by particular objective weights.