Research Area:  Machine Learning

Abstract:

In this paper, we introduce a novel reinforcement learning (RL) scheme for linear continuous-time dynamical systems. Different from traditional batch learning algorithms, an incremental learning approach is developed, which provides a more efficient way to tackle the on-line learning problem in realworld applications. We provide concrete convergence and robust analysis on this incremental-learning algorithm. An extension to solving robust optimal control problems is also given. Two simulation examples are also given to illustrate the effectiveness of our theoretical result.

Keywords:  
Reinforcement Learning
Linear Continuous-Time Systems
Incremental Learning
Machine Learning
Deep Learning

Author(s) Name:  Tao Bian; Zhong-Ping Jiang

Publisher name:  IEEE

DOI:  10.1109/JAS.2019.1911390

Volume Information:  Volume: 6, Issue: 2, March 2019, Page(s): 433 - 440

Paper Link:   https://ieeexplore.ieee.org/abstract/document/8651896