A Q-Learning Algorithm for Discrete-Time Linear-Quadratic Control with Random Parameters of Unknown Distribution: Convergence and Stabilization
From MaRDI portal
Publication:5093265
DOI10.1137/20M1379605zbMath1493.49034arXiv2011.04970OpenAlexW4297626836MaRDI QIDQ5093265
Kai Du, Fu Zhang, Qingxin Meng
Publication date: 26 July 2022
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2011.04970
Sensitivity, stability, well-posedness (49K40) Optimal feedback synthesis (49N35) Stabilization of systems by feedback (93D15) Linear-quadratic optimal control problems (49N10) Stochastic learning and adaptive control (93E35)
Related Items (2)
Deterministic optimal control for discrete-time systems with multiplicative noises and random coefficients ⋮ A distributed stochastic approximation algorithm for stochastic LQ control with unknown uncertainty
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Infinite horizon optimal control of linear discrete time systems with stochastic parameters
- Discrete-time optimal control with control-dependent noise and generalized Riccati difference equations
- Asynchronous stochastic approximation and Q-learning
- Stochastic approximation and its applications
- On adaptive linear-quadratic regulators
- A unified approach to the theory of sampling systems
- Optimization of stochastic systems. Topics in discrete-time systems
- Indefinite Mean-Field Stochastic Linear-Quadratic Optimal Control: From Finite Horizon to Infinite Horizon
- Linear Quadratic Problems with Indefinite Cost for Discrete Time Systems
- The equivalent discrete-time optimal control problem for continuous-time systems with stochastic parameters
- Stabilization of some stochastic discrete–time control systems
- Stabilization of deterministic and stochastic-parameter discrete systems
- Optimal stochastic adaptive control with quadratic index
- Control of randomly varying systems with prescribed degree of stability
- The uncertainty threshold principle: Some fundamental limitations of optimal decision making under dynamic uncertainty
- Further results on the uncertainty threshold principle
- Stochastic controllability of linear discrete systems with multiplicative noise
- Stochastic Linear Quadratic Regulators with Indefinite Control Weight Costs
- On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
- Adaptive continuous-time linear quadratic Gaussian control
- Indefinite Stochastic Linear Quadratic Control and Generalized Differential Riccati Equation
- An actively adaptive control policy for linear models
- An actively adaptive control for linear systems with random parameters via the dual control approach
- A Stochastic Approximation Method
This page was built for publication: A Q-Learning Algorithm for Discrete-Time Linear-Quadratic Control with Random Parameters of Unknown Distribution: Convergence and Stabilization
