On adaptive linear-quadratic regulators
From MaRDI portal
Abstract: Performance of adaptive control policies is assessed through the regret with respect to the optimal regulator, which reflects the increase in the operating cost due to uncertainty about the dynamics parameters. However, available results in the literature do not provide a quantitative characterization of the effect of the unknown parameters on the regret. Further, there are problems regarding the efficient implementation of some of the existing adaptive policies. Finally, results regarding the accuracy with which the system's parameters are identified are scarce and rather incomplete. This study aims to comprehensively address these three issues. First, by introducing a novel decomposition of adaptive policies, we establish a sharp expression for the regret of an arbitrary policy in terms of the deviations from the optimal regulator. Second, we show that adaptive policies based on slight modifications of the Certainty Equivalence scheme are efficient. Specifically, we establish a regret of (nearly) square-root rate for two families of randomized adaptive policies. The presented regret bounds are obtained by using anti-concentration results on the random matrices employed for randomizing the estimates of the unknown parameters. Moreover, we study the minimal additional information on dynamics matrices that using them the regret will become of logarithmic order. Finally, the rates at which the unknown parameters of the system are being identified are presented.
Recommendations
Cites work
- A note on the structure of two subsets of the parameter space in adaptive control problems
- Adaptive Linear Quadratic Gaussian Control: The Cost-Biased Approach Revisited
- Adaptive continuous-time linear quadratic Gaussian control
- Adaptive control of linear time invariant systems: the ``Bet on the best principle
- Adaptive control with the stochastic approximation algorithm: Geometry and convergence
- Adaptive systems, lack of persistency of excitation and bursting phenomena
- Asymptotically efficient adaptive allocation rules
- Asymptotically efficient adaptive control in stochastic regression models
- Convergence and logarithm laws of self-tuning regulators
- Convergence of adaptive control schemes using least-squares parameter estimates
- Convergence properties of the Riccati difference equation in optimal filtering of nonstabilizable systems
- Dual effect, certainty equivalence, and separation in stochastic control
- Extended least squares and their applications to adaptive control and prediction in linear systems
- Finite time identification in unstable linear systems
- Finite-Time Adaptive Stabilization of Linear Systems
- Global adaptive pole placement: Detailed analysis of a first-order system
- Least squares estimates in stochastic regression models with applications to identification and control of dynamic systems
- Linear Thompson sampling revisited
- On the necessity of identifying the true parameter in adaptive LQ control
- Online learning in the embedded manifold of low-rank matrices
- Optimality of Fast-Matching Algorithms for Random Networks With Applications to Structural Controllability
- Parallel Recursive Algorithms in Asymptotically Efficient Adaptive Control of Linear Stochastic Systems
- scientific article; zbMATH DE number 3982362 (Why is no real title available?)
- scientific article; zbMATH DE number 1095138 (Why is no real title available?)
- scientific article; zbMATH DE number 4120105 (Why is no real title available?)
- scientific article; zbMATH DE number 4197903 (Why is no real title available?)
- Riccati equations in optimal filtering of nonstabilizable systems having singular state transition matrices
- The AAstrom-Wittenmark self-tuning regulator revisited and ELS-based adaptive trackers
- Weighted Estimation and Tracking for ARMAX Models
Cited in
(12)- Input perturbations for adaptive control and learning
- Performance analysis of the compressed distributed least squares algorithm
- scientific article; zbMATH DE number 3941380 (Why is no real title available?)
- scientific article; zbMATH DE number 1079096 (Why is no real title available?)
- A Q-Learning Algorithm for Discrete-Time Linear-Quadratic Control with Random Parameters of Unknown Distribution: Convergence and Stabilization
- Adaptive Control by Regulation-Triggered Batch Least Squares
- Regret bounds for online-learning-based linear quadratic control under database attacks
- On the relation between dynamic regret and closed-loop stability
- Joint learning of linear time-invariant dynamical systems
- Learning decentralized linear quadratic regulators with \(\sqrt{T}\) regret
- Identification of non-causal systems with random switching modes
- Logarithmic regret in the ergodic Avellaneda-Stoikov market making model
This page was built for publication: On adaptive linear-quadratic regulators
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2184529)
