Robust Output Regulation and Reinforcement Learning-Based Output Tracking Design for Unknown Linear Discrete-Time Systems
From MaRDI portal
Publication:6053282
Abstract: In this paper, we investigate the optimal output tracking problem for linear discrete-time systems with unknown dynamics using reinforcement learning and robust output regulation theory. This output tracking problem only allows to utilize the outputs of the reference system and the controlled system, rather than their states, and differs from most existing tracking results that depend on the state of the system. The optimal tracking problem is formulated into a linear quadratic regulation problem by proposing a family of dynamic discrete-time controllers. Then, it is shown that solving the output tracking problem is equivalent to solving output regulation equations, whose solution, however, requires the knowledge of the complete and accurate system dynamics. To remove such a requirement, an off-policy reinforcement learning algorithm is proposed using only the measured output data along the trajectories of the system and the reference output. By introducing re-expression error and analyzing the rank condition of the parameterization matrix, we ensure the uniqueness of the proposed RL based optimal control via output feedback.
Cited in
(22)- Adaptive Optimal Control of Linear Discrete-Time Networked Control Systems with Two-Channel Stochastic Dropouts
- Data-driven optimal output regulation for unknown linear discrete-time systems based on parameterization approach
- Distributed output data-driven optimal robust synchronization of heterogeneous multi-agent systems
- Specified convergence rate guaranteed output tracking of discrete-time systems via reinforcement learning
- Control policy learning design for vehicle urban positioning via BeiDou navigation
- Incremental reinforcement learning and optimal output regulation under unmeasurable disturbances
- Output‐feedback robust control of systems with uncertain dynamics via data‐driven policy learning
- Optimal dynamic output feedback control of unknown linear continuous-time systems by adaptive dynamic programming
- Adaptive optimal tracking control of networked linear systems under two-channel stochastic dropouts
- Finite-horizon Q-learning for discrete-time zero-sum games with application to \(H_{\infty}\) control
- \(\mathcal{L}_2\) gain tracking control of linear completely unknown discrete-time networked control systems with dropout
- Homotopic policy iteration learning for linear continuous-time zero-sum games via state and output feedback
- Data-driven adaptive optimal output tracking with assured convergence rate
- Distributed output optimal robust time-varying formation tracking control for heterogeneous multi-agent systems based on reinforcement learning
- Non-zero-sum games in continuous-time nonlinear systems: multiplayer cascaded solutions
- Adaptive dynamic programming for unknown continuous-time nonlinear systems via bias-policy iteration
- A deep reinforcement learning control framework for a partially observable system: experimental validation on a rotary flexible link system
- Data-driven dynamic output feedback Nash strategy for multi-player non-zero-sum games
- Fully distributed cooperative output regulation of heterogeneous periodic linear multi-agent systems with input saturation
- Scaling policy iteration based reinforcement learning for unknown discrete-time linear systems
- Adaptive dynamic programming infinite-horizon optimal tracking control for stochastic linear discrete-time systems
- Specified convergence rate guaranteed data-driven output regulation with partially unknown system matrices: an LMI-based approach
This page was built for publication: Robust Output Regulation and Reinforcement Learning-Based Output Tracking Design for Unknown Linear Discrete-Time Systems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6053282)
