.png){kind=icon}
返回
Reinforcement Learning-Based Nearly Optimal Control for Constrained-Input Partially Unknown Systems Using Differentiator
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2019.2957287.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this article, a synchronous reinforcementlearning-based algorithm is developed for input-constrained partially unknown systems. The proposed control also alleviates the need for an initial stabilizing control. A first-order robust exact differentiator is employed to approximate unknown drift dynamics. Critic, actor, and disturbance neural networks (NNs) are established to approximate the value function, the control policy, and the disturbance policy, respectively. The HamiltonJacobi-Isaacs equation is solved by applying the value function approximation technique. The stability of the closed-loop system can be ensured. The state and weight errors of the three NNs are all uniformly ultimately bounded. Finally, the simulation results are provided to verify the effectiveness of the proposed method.
Keyword:
Artificial neural networks
Heuristic algorithms
Optimal control
Games
Performance analysis
Approximation algorithms
Game theory
First-order robust exact differentiator (RED)
input constraint
neural network (NN)
reinforcement learning (RL)
two-player zero-sum game
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
.png){kind=icon}
分享收藏分享收藏Adaptive Neural Network Control of AUVs With Control Input Nonlinearities Using Reinforcement Learning基于强化学习的auv控制输入非线性自适应神经网络控制
OAAI
OAAI分享收藏Ac-Electrogravimetry Study of Electroactive Thin Films. II. Application to Polypyrrole电活性薄膜的交流电重分析研究。二。聚吡咯的应用
PREAI
分享收藏Adaptive Neural Network Control of an Uncertain Robot With Full-State Constraints具有全状态约束的不确定机器人自适应神经网络控制
PREAI
分享收藏
查看更多内容