Model-free optimal control of discrete-time systems with additive and multiplicative noises
From MaRDI portal
Publication:2103660
DOI10.1016/J.AUTOMATICA.2022.110685zbMATH Open1505.93287arXiv2008.08734OpenAlexW4308902993MaRDI QIDQ2103660FDOQ2103660
Authors: Jing Lai, Junlin Xiong, Zhan Shu 
Publication date: 9 December 2022
Published in: Automatica (Search for Journal in Brave)
Abstract: This paper investigates the optimal control problem for a class of discrete-time stochastic systems subject to additive and multiplicative noises. A stochastic Lyapunov equation and a stochastic algebra Riccati equation are established for the existence of the optimal admissible control policy. A model-free reinforcement learning algorithm is proposed to learn the optimal admissible control policy using the data of the system states and inputs without requiring any knowledge of the system matrices. It is proven that the learning algorithm converges to the optimal admissible control policy. The implementation of the model-free algorithm is based on batch least squares and numerical average. The proposed algorithm is illustrated through a numerical example, which shows our algorithm outperforms other policy iteration algorithms.
Full work available at URL: https://arxiv.org/abs/2008.08734
Recommendations
- Optimal control of unknown discrete-time linear systems with additive noise
- Robust reinforcement learning for stochastic linear quadratic control with multiplicative noise
- \(\mathrm{H}_\infty\) control of linear discrete-time systems: off-policy reinforcement learning
- A reinforcement learning-based scheme for direct adaptive optimal control of linear stochastic systems
- Reinforcement learning for adaptive optimal control of continuous-time linear periodic systems
reinforcement learningmodel-freeadditive and multiplicative noisesstochastic linear quadratic regulator
Linear-quadratic optimal control problems (49N10) Discrete-time control/observation systems (93C55) Optimal stochastic control (93E20)
Cites Work
- High-dimensional probability. An introduction with applications in data science
- Stochastic Receding Horizon Control of Constrained Linear Systems With State and Control Multiplicative Noise
- Subexponentiality of the product of independent random variables
- 10.1162/1532443041827907
- Robust shortest path planning and semicontractive dynamic programming
- Generalized value iteration for discounted optimal control with stability analysis
- Mean square stability conditions for discrete stochastic bilinear systems
- Output feedback Q-learning for discrete-time linear zero-sum games with application to the \(H_\infty\) control
- Learning Optimal Controllers for Linear Systems With Multiplicative Noise via Policy Gradient
- Model-free design of stochastic LQR controller from a primal-dual optimization perspective
- Deep reinforcement learning for wireless sensor scheduling in cyber-physical systems
- Primal-Dual Q-Learning Framework for LQR Design
Cited In (11)
- Stochastic LQ optimal control for Markov jumping systems with multiplicative noise using reinforcement learning
- Robust Optimal Control for Discrete-Time LTI Systems Over Multiple Additive White Gaussian Noise Channels
- Deterministic optimal control for discrete-time systems with multiplicative noises and random coefficients
- Optimal control of unknown discrete-time linear systems with additive noise
- Solving optimal predictor-feedback control using approximate dynamic programming
- Policy gradient methods for discrete time linear quadratic regulator with random parameters
- Reinforcement learning-based optimal control for Markov jump systems with completely unknown dynamics
- Asynchronous deep reinforcement learning with gradient sharing for state of charge balancing of multiple batteries in cyber-physical electric vehicles
- Robust reinforcement learning for stochastic linear quadratic control with multiplicative noise
- Specified convergence rate guaranteed output tracking of discrete-time systems via reinforcement learning
- Model-free control of nonlinear stochastic systems with discrete-time measurements
This page was built for publication: Model-free optimal control of discrete-time systems with additive and multiplicative noises
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2103660)
