This paper proposes a lightweight reinforcement network (LRN) and auxiliary label distribution learning (ALDL) based robust facial expression recognition (FER) method. Our designed representation reinforcement (RR) network mainly comprises two modules, i.e., the RR module and the auxiliary label space construction (ALSC) module. The RR module highlights key feature messaging nodes in feature maps, and ALSC allows multiple labels with different intensities to be linked to one expression. Therefore, LRN has a more robust feature extraction capability when model parameters are greatly reduced, and ALDL is proposed to contribute to the training effect of LRN in the condition of ambiguous training data. We tested our method on FER-Plus and RAF-DB datasets, and the experiment demonstrates the feasibility of our method in practice during rehabilitation robots.