Optimal polynomial feedback laws for finite horizon control problems
From MaRDI portal
Publication:6072899
Abstract: A learning technique for finite horizon optimal control problems and its approximation based on polynomials is analyzed. It allows to circumvent, in part, the curse dimensionality which is involved when the feedback law is constructed by using the Hamilton-Jacobi-Bellman (HJB) equation. The convergence of the method is analyzed, while paying special attention to avoid the use of a global Lipschitz condition on the nonlinearity which describes the control system. The practicality and efficiency of the method is illustrated by several examples. For two of them a direct approach based on the HJB equation would be unfeasible.
Recommendations
- Approximate finite-horizon optimal control without PDEs
- Approximating optimal feedback controllers of finite horizon control problems using hierarchical tensor formats
- Approximation of optimal feedback control: a dynamic programming approach
- Polynomial approximation of high-dimensional Hamilton-Jacobi-Bellman equations and applications to feedback control of semilinear parabolic PDEs
- Numerical study of polynomial feedback laws for a bilinear control problem
Cites work
- scientific article; zbMATH DE number 2050349 (Why is no real title available?)
- scientific article; zbMATH DE number 7370565 (Why is no real title available?)
- scientific article; zbMATH DE number 3353830 (Why is no real title available?)
- A neural network-based policy iteration algorithm with global \(H^2\)-superlinear convergence for stochastic games on domains
- Adaptive deep learning for high-dimensional Hamilton-Jacobi-Bellman equations
- Algorithm for Hamilton-Jacobi equations in density space via a generalized Hopf formula
- Algorithm for overcoming the curse of dimensionality for state-dependent Hamilton-Jacobi equations
- Algorithm for overcoming the curse of dimensionality for time-dependent non-convex Hamilton-Jacobi equations arising from optimal control and differential games problems
- Algorithms for overcoming the curse of dimensionality for certain Hamilton-Jacobi equations arising in control theory and elsewhere
- Algorithms of data generation for deep learning and feedback design: a survey
- An adaptive sparse grid semi-Lagrangian scheme for first order Hamilton-Jacobi Bellman equations
- An efficient DP algorithm on a tree-structure for finite horizon optimal control problems
- An efficient policy iteration algorithm for dynamic programming equations
- Analysis of the Barzilai-Borwein step-sizes for problems in Hilbert spaces
- Approximating optimal feedback controllers of finite horizon control problems using hierarchical tensor formats
- Controlled Markov processes and viscosity solutions
- Convergence Properties of Policy Iteration
- Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis
- Discrete approximations of the Hamilton-Jacobi equation for an optimal control problem of a differential-algebraic system
- Error analysis for POD approximations of infinite horizon problems via the dynamic programming approach
- First-order methods in optimization
- Galerkin approximations of the generalized Hamilton-Jacobi-Bellman equation
- HJB-POD-Based Feedback Design for the Optimal Control of Evolution Problems
- Mitigating the curse of dimensionality: sparse grid characteristics method for optimal feedback control and HJB equations
- On the Convergence of Policy Iteration in Stationary Dynamic Programming
- Overcoming the curse of dimensionality for some Hamilton-Jacobi partial differential equations via neural network architectures
- Polynomial approximation of high-dimensional Hamilton-Jacobi-Bellman equations and applications to feedback control of semilinear parabolic PDEs
- Robust Feedback Control of Nonlinear PDEs by Numerical Approximation of High-Dimensional Hamilton--Jacobi--Isaacs Equations
- Semi-Lagrangian schemes for Hamilton-Jacobi equations, discrete representation formulae and Godunov methods
- Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation
- Smooth analysis in Banach spaces
- Solving high-dimensional partial differential equations using deep learning
- Sparse Reconstruction by Separable Approximation
- Suboptimal feedback control of PDEs by solving HJB equations on adaptive sparse grids
- Tensor decomposition methods for high-dimensional Hamilton-Jacobi-Bellman equations
- The Barzilai and Borwein Gradient Method for the Large Scale Unconstrained Minimization Problem
- The Max-Plus Finite Element Method for Solving Deterministic Optimal Control Problems: Basic Properties and Convergence Analysis
- Two-Point Step Size Gradient Methods
Cited in
(6)- scientific article; zbMATH DE number 4051489 (Why is no real title available?)
- Optimal regulation using measurement feedback: a polynomial approach
- Polynomial Optimization of Stochastic Feedback Control for Stable Plants
- Optimal control for a polynomial system with a quadratic criterion over infinite horizon
- Consistent smooth approximation of feedback laws for infinite horizon control problems with non-smooth value functions
- Numerical realization of the Mortensen observer via a Hessian-augmented polynomial approximation of the value function
This page was built for publication: Optimal polynomial feedback laws for finite horizon control problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6072899)
