期刊
IEEE TRANSACTIONS ON FUZZY SYSTEMS
卷 28, 期 4, 页码 658-672出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TFUZZ.2019.2912349
关键词
Adaptive systems; Computer architecture; Dynamic programming; Mobile robots; Adaptive dynamic programming (ADP); convergence analysis; eligibility traces; mobile robot; recurrent neuro-fuzzy (RNF); Takagi-Sugeno (T-S) neuro-fuzzy
资金
- Missouri University of Science and Technology Intelligent Systems Center
- Mary K. FinleyMissouri Endowment
- Lifelong Learning Machines Program from DARPA/Microsystems Technology Office
- Army Research Laboratory (ARL) [W911NF-18-2-0260]
- National Science Foundation
- Basra Oil Company (BOC) in Iraq
- Higher Committee for Educational Development (HCED)
In recent years, a gradient of the n-step temporaldifference [TD(lambda)] learning has been developed to present an advanced adaptive dynamic programming (ADP) algorithm, called value-gradient learning [VGLl]. In this paper, we improve the VGLl architecture, which is called the single adaptive actor network [SNVGLl] because it has only a single approximator function network (critic) instead of dual networks (critic and actor) as in VGLl. Therefore, SNVGLl has lower computational requirements when compared to VGLl. Moreover, in this paper, a recurrent hybrid neuro-fuzzy (RNF) and a first-order Takagi-Sugeno RNF (TSRNF) are derived and implemented to build the critic and actor networks. Furthermore, we develop the novel study of the theoretical convergence proofs for both VGLl and SNVGLl under certain conditions. In this paper, mobile robot simulation model (model based) is used to solve the optimal control problem for affine nonlinear discrete-time systems. Mobile robot is exposed various noise levels to verify the performance and to validate the theoretical analysis.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据