Transfer learning of state-based potential games for process optimization in decentralized manufacturing systems

TL;DR

This paper introduces a transfer learning method within state-based potential games to enhance distributed process optimization in manufacturing, enabling knowledge sharing among players for faster learning and better efficiency.

Contribution

It develops a novel transfer learning framework for state-based potential games with predefined and dynamic similarity criteria, improving decentralized manufacturing optimization.

Findings

Enhanced production efficiency in experiments

Reduced power consumption compared to baseline

Faster convergence in learning processes

Abstract

This paper presents a novel online transfer learning approach in state-based potential games (TL-SbPGs) for distributed self-optimization in manufacturing systems. The approach targets practical industrial scenarios where knowledge sharing among similar players enhances learning in large-scale and decentralized environments. TL-SbPGs enable players to reuse learned policies from others, which improves learning outcomes and accelerates convergence. To accomplish this goal, we develop transfer learning concepts and similarity criteria for players, which offer two distinct settings: (a) predefined similarities between players and (b) dynamically inferred similarities between players during training. The applicability of the SbPG framework to transfer learning is formally established. Furthermore, we present a method to optimize the timing and weighting of knowledge transfer. Experimental results from a laboratory-scale testbed show that TL-SbPGs improve production efficiency and reduce power consumption compared to vanilla SbPGs.