Journal
NEURAL NETWORKS
Volume 145, Issue -, Pages 33-41Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2021.10.009
Keywords
Complementary learning; Hippocampus and neocortex learning systems; Q-learning; Inverse reinforcement learning; Batch least squares; Gradient-descent rule
Ask authors/readers for more resources
This paper proposes a complementary learning scheme for experience transference of unknown continuous time linear systems, inspired by the learning properties of hippocampus and neocortex via the striatum. The model involves optimizing controller data for the hippocampus and implementing a Q reinforcement learning algorithm for the neocortex, with an inverse reinforcement learning algorithm for complementary learning. Convergence of the proposed approach is analyzed using Lyapunov recursions, and simulations are carried out to verify its effectiveness.
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. (C) 2021 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available