Multiobjective Reinforcement Learning for Reconfigurable Adaptive Optimal Control of Manufacturing Processes
This addresses the challenge of dynamically adjusting control strategies in industrial manufacturing processes, though it appears incremental as it builds on existing reinforcement learning methods for a specific domain.
The paper tackles the problem of adaptive optimal control in manufacturing where multiple conflicting objectives with unknown or changing weights must be considered, proposing a novel model-free multiobjective reinforcement learning approach that enables sample-efficient learning across sequences of control configurations.
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.