On the Convergence of Policy Iteration in Stationary Dynamic Programming
From MaRDI portal
compact action spaceerror boundsfinite state Markovian decision problemNewton-Kantorovich iteration procedurepartially ordered normed linear spacespolicy iteration methodprogramming in abstract spacesrate of convergencestationary dynamic programming
Rate of convergence, degree of approximation (41A25) Normed linear spaces and Banach spaces; Banach lattices (46B99) Newton-type methods (49M15) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40) Minimax problems in mathematical programming (90C47) Programming in abstract spaces (90C48)
Cited in
(54)- The variational calculus and approximation in policy space for Markovian decision processes
- Discrete dynamic programming and viscosity solutions of the Bellman equation
- On the convergence of policy iteration for controlled diffusions
- Policy iteration and Newton-Raphson methods for Markov decision processes under average cost criterion
- Numerical approximation of equations involving minimal/maximal operators by successive solution of obstacle problems
- A semi-Lagrangian scheme for a modified version of the Hughes' model for Pedestrian flow
- Optimal consumption under uncertainty, liquidity constraints, and bounded rationality
- Domain decomposition based parallel Howard's algorithm
- A neural network-based policy iteration algorithm with global \(H^2\)-superlinear convergence for stochastic games on domains
- Optimal price-threshold control for battery operation with aging phenomenon: a quasiconvex optimization approach
- Applications of Markov chain approximation methods to optimal control problems in economics
- Continuous vs. discrete time: some computational insights
- Multilevel techniques for the solution of HJB minimum-time control problems
- A mean field games model for finite mixtures of Bernoulli and categorical distributions
- The primal-dual active set method for a class of nonlinear problems with T-monotone operators
- On linear and super-linear convergence of natural policy gradient algorithm
- Optimal investment strategies for pension funds with regulation-conform dynamic pension payment management in the absence of guarantees
- Policy iteration method for time-dependent mean field games systems with non-separable Hamiltonians
- Mathematical programming based debugging
- A Fixed Point Approach to Undiscounted Markov Renewal Programs
- A policy iteration method for mean field games
- (Approximate) iterated successive approximations algorithm for sequential decision processes
- Survey of linear programming for standard and nonstandard Markovian control problems. Part I: Theory
- A semi-Lagrangian algorithm in policy space for hybrid optimal control problems
- Multigrid methods for two-player zero-sum stochastic games.
- Tensor decomposition methods for high-dimensional Hamilton-Jacobi-Bellman equations
- Two-scale methods for convex envelopes
- Undiscounted control policy generation for continuous-valued optimal control by approximate dynamic programming
- scientific article; zbMATH DE number 7626790 (Why is no real title available?)
- Approximations and optimal control for state-dependent limited processor sharing queues
- Approximating optimal feedback controllers of finite horizon control problems using hierarchical tensor formats
- Unique Tarski Fixed Points
- Exponential convergence and stability of Howard's policy improvement algorithm for controlled diffusions
- Recent Results in the Approximation of Nonlinear Optimal Control Problems
- A discrete Hughes model for pedestrian flow on graphs
- An Accelerated Value/Policy Iteration Scheme for Optimal Control Problems and Games
- NUMERICAL METHODS FOR DIFFERENTIAL GAMES BASED ON PARTIAL DIFFERENTIAL EQUATIONS
- Value-Gradient Based Formulation of Optimal Control Problem and Machine Learning Algorithm
- Optimal polynomial feedback laws for finite horizon control problems
- A note on generalized second-order value iteration in Markov decision processes
- Approximating the stationary Bellman equation by hierarchical tensor products
- Consistent smooth approximation of feedback laws for infinite horizon control problems with non-smooth value functions
- Numerical Hopf-Lax formulae for Hamilton-Jacobi equations on unstructured geometries
- Dynamic perturbation
- Modified monotone policy iteration for interpretable policies in Markov decision processes and the impact of state ordering rules
- Policy iteration for exploratory Hamilton-Jacobi-Bellman equations
- Policy iteration for the deterministic control problems -- a viscosity approach
- Convergence analysis for entropy-regularized control problems: a probabilistic approach
- A policy iteration method for inverse mean field games
- Back in time. Fast. Accelerated time iterations
- Semismooth Newton methods for risk-averse Markov decision processes
- The Howard's policy iteration and convergence for optimal dividend under compound-Poisson model
- A numerical method for pricing European options with proportional transaction costs
- Rates of convergence for the policy iteration method for mean field games systems
This page was built for publication: On the Convergence of Policy Iteration in Stationary Dynamic Programming
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4198357)
