A complementary learning approach for expertise transference of human-optimized controllers. (January 2022)

• Record Type: Journal Article
• Authors: Perrusquía, Adolfo
• Is Part Of: Neural networks. Volume 145(2022)
• Page Start: 33
• Page End: 41
• Publication Date: 2022-01
• Subjects: Complementary learning -- Hippocampus and neocortex learning systems -- Q-learning -- Inverse reinforcement learning -- Batch least squares -- Gradient-descent rule; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2021.10.009
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: In this paper, a complementary learning scheme for experience transference of unknown continuous-time linear systems is proposed. The algorithm is inspired in the complementary learning properties that exhibit the hippocampus and neocortex learning systems via the striatum. The hippocampus is modelled as pattern-separated data of a human optimized controller. The neocortex is modelled as a Q-reinforcement learning algorithm which improves the hippocampus control policy. The complementary learning (striatum) is designed as an inverse reinforcement learning algorithm which relates the hippocampus and neocortex learning models to seek and transfer the weights of the hidden expert's utility function. Convergence of the proposed approach is analysed using Lyapunov recursions. Simulations are given to verify the proposed approach.