首页|A complementary learning approach for expertise transference of human-optimized controllers
A complementary learning approach for expertise transference of human-optimized controllers
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NSTL
Elsevier
? 2021 Elsevier LtdIn 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.
Batch least squaresComplementary learningGradient-descent ruleHippocampus and neocortex learning systemsInverse reinforcement learningQ-learning
Perrusquia A.
展开 >
School of Aerospace Transport and Manufacturing Cranfield University
NSTL
Elsevier
