Reinforcement learning for soft sensor design through autonomous cross-domain data selection

Junyao Xie, Oguzhan Dogru, Biao Huang, Chris Godwaldt, Brett Willms

Abstract: Highlights•A reinforcement learning frame for autonomous cross-domain soft sensing is proposed.•A Markov decision process formulation is developed.•Asynchronous advantage selector-actor-critic methods are proposed.•A novel reward is defined by combining the correlation and prediction error metrics.•A numerical simulation and an industrial case study verify the proposed methods.