Robust Control of Unknown Observable Nonlinear Systems Solved as a Zero-Sum Game
An optimal robust control solution for general nonlinear systems with unknown but observable dynamics is advanced here. The underlying Hamilton-Jacobi-Isaacs (HJI) equation of the corresponding zero-sum two-player game (ZS-TP-G) is learned using a Q-learning-based approach employing only input-outpu...
Main Authors: | Mircea-Bogdan Radac, Timotei Lala |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9268935/ |
Similar Items
-
Learning Output Reference Model Tracking for Higher-Order Nonlinear Systems with Unknown Dynamics
by: Mircea-Bogdan Radac, et al.
Published: (2019-06-01) -
Virtual State Feedback Reference Tuning and Value Iteration Reinforcement Learning for Unknown Observable Systems Control
by: Mircea-Bogdan Radac, et al.
Published: (2021-02-01) -
Addendum: Mircea-Bogdan Radac and Timotei Lala. Learning Output Reference Model Tracking for Higher-order Nonlinear Systems with Unknown Dynamics. <i>Algorithms</i> 2019, <i>12</i>, 121
by: Mircea-Bogdan Radac, et al.
Published: (2019-10-01) -
Data-Driven Model-Free Tracking Reinforcement Learning Control with VRFT-based Adaptive Actor-Critic
by: Mircea-Bogdan Radac, et al.
Published: (2019-04-01) -
Data-Driven Integral Reinforcement Learning for Continuous-Time Non-Zero-Sum Games
by: Yongliang Yang, et al.
Published: (2019-01-01)