Abstract: This paper presents a new theory, known as robust dynamic pro- gramming, for a class of continuous-time dynamical systems. Different from traditional dynamic programming (DP) methods, this new theory serves as a fundamental tool to analyze the robustness of DP algorithms, and in par- ticular, to develop novel adaptive optimal control and reinforcement learning methods. In order to demonstrate the potential of this new framework, four illustrative applications in the fields of stochastic optimal control and adaptive DP are presented. Three numerical examples arising from both finance and engineering industries are also given, along with several possible extensions of the proposed framework.
Recommendations
- Robust adaptive dynamic programming for linear and nonlinear systems: an overview
- scientific article; zbMATH DE number 1342078
- Robust Dynamic Programming
- Reinforcement learning for adaptive optimal control of continuous-time linear periodic systems
- Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design
Cites work
- L₂-gain and passivity techniques in nonlinear control
- Abstract dynamic programming
- Adaptive Control Design and Analysis
- Adaptive dynamic programming and optimal control of nonlinear nonaffine systems
- Adaptive nonlinear control without overparametrization
- An analysis of temporal-difference learning with function approximation
- Asynchronous stochastic approximation and Q-learning
- Calculus of variations and optimal control theory. A concise introduction
- Continuous-time mean-variance portfolio selection: a stochastic LQ framework
- Continuous-time stochastic control and optimization with financial applications
- Dynamic programming and optimal control. Vol. 1.
- Ergodic control of diffusion processes
- Ergodic control of diffusion processes.
- Further properties of nonzero-sum differential games
- scientific article; zbMATH DE number 3126094 (Why is no real title available?)
- scientific article; zbMATH DE number 3148886 (Why is no real title available?)
- scientific article; zbMATH DE number 5347321 (Why is no real title available?)
- scientific article; zbMATH DE number 3719745 (Why is no real title available?)
- scientific article; zbMATH DE number 1321699 (Why is no real title available?)
- scientific article; zbMATH DE number 1182386 (Why is no real title available?)
- scientific article; zbMATH DE number 1972910 (Why is no real title available?)
- scientific article; zbMATH DE number 1547390 (Why is no real title available?)
- scientific article; zbMATH DE number 3992716 (Why is no real title available?)
- scientific article; zbMATH DE number 3439537 (Why is no real title available?)
- scientific article; zbMATH DE number 3400258 (Why is no real title available?)
- Kronecker products and matrix calculus in system theory
- Neural robust stabilization via event-triggering mechanism and adaptive learning technique
- Neuro-Dynamic Programming: An Overview and Recent Results
- Nonlinear Control of Dynamic Networks
- Nonlinear control systems. II
- Nonlinear systems.
- Nonlinear systems. Analysis, stability, and control
- Nonzero-sum differential games
- On the Theory of Dynamic Programming
- Reinforcement learning in robust Markov decision processes
- Reinforcement learning. An introduction
- Robust adaptive dynamic programming
- Robust adaptive dynamic programming for linear and nonlinear systems: an overview
- Robust Control of Markov Decision Processes with Uncertain Transition Matrices
- Robust Dynamic Programming
- Robust pole placement in LMI regions
- Small-gain theorem for ISS systems and applications
- Stabilization in spite of matched unmodeled dynamics and equivalent definition of input-to-state stability
- Stochastic Approximation for Nonexpansive Maps: Application to Q-Learning Algorithms
- Stochastic Optimal Control and Estimation Methods Adapted to the Noise Characteristics of the Sensorimotor System
- Stochastic stability of differential equations. With contributions by G. N. Milstein and M. B. Nevelson
- The maximally achievable accuracy of linear optimal regulators and linear optimal filters
- Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design
Cited in
(21)- The dynamic programming approach to multi-model robust optimization
- A model for system uncertainty in reinforcement learning
- Adaptive optimal output regulation of linear discrete-time systems based on event-triggered output-feedback
- Learning-based adaptive optimal output regulation of linear and nonlinear systems: an overview
- Modeling and computation of an integral operator Riccati equation for an infinite-dimensional stochastic differential equation governing streamflow discharge
- Resilient reinforcement learning and robust output regulation under denial-of-service attacks
- Human motor learning is robust to control-dependent noise
- A dynamic programming approach to adjustable robust optimization
- A dynamic programming approach for a class of robust optimization problems
- scientific article; zbMATH DE number 1342078 (Why is no real title available?)
- Robust reinforcement learning for stochastic linear quadratic control with multiplicative noise
- Robust Dual Dynamic Programming
- Adaptive Optimal Control of Linear Discrete-Time Networked Control Systems with Two-Channel Stochastic Dropouts
- Robust optimal control of logical control networks with function perturbation
- Specified convergence rate guaranteed output tracking of discrete-time systems via reinforcement learning
- An adaptive dynamic programming-based algorithm for infinite-horizon linear quadratic stochastic optimal control problems
- Data-driven direct adaptive risk-sensitive control of stochastic systems
- Stochastic linear quadratic optimal control for continuous-time systems via reinforcement learning
- On-policy and off-policy value iteration algorithms for stochastic zero-sum dynamic games
- Stochastic adaptive linear quadratic nonzero-sum differential games
- An online value iteration method for stochastic linear quadratic control with multiplicative noise
This page was built for publication: Continuous-time robust dynamic programming
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5205609)
