Truncated policy iteration methods
Policy iteration methods are important but often computationally expensive approaches for solving certain stochastic optimization problems. Modified policy iteration methods have been proposed to reduce the storage and computational burden. The asymptotic speed-of-convergence of such methods is, however, not well understood. In this paper we show how modified policy iteration methods may be constructed to achieve a preassigned rate-of-convergence. Our analysis provides a framework for analyzing the local behavior of such methods and provides impetus for perhaps more computationally efficient procedures than currently exist.
- Policy iteration for bounded-parameter POMDPs
- Policy iteration in finite templates domain
- 10.1162/1532443041827907
- Approximate policy iteration: a survey and some new methods
- Reduced complexity dynamic programming based on policy iteration
- Policy iteration accelerated with Krylov methods
- Analytic policy function iteration
- A sums-of-squares extension of policy iterations
- Policy iteration based on stochastic factorization
- Accelerated modified policy iteration algorithms for Markov decision processes
- Contraction Mappings in the Theory Underlying Dynamic Programming
- scientific article; zbMATH DE number 3148886 (Why is no real title available?)
- scientific article; zbMATH DE number 3607838 (Why is no real title available?)
- scientific article; zbMATH DE number 3628710 (Why is no real title available?)
- Inexact Newton Methods
- Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
- Hierarchic Markov processes and their applications in replacement models
- A K-step look-ahead analysis of value iteration algorithms for Markov decision processes
- (Approximate) iterated successive approximations algorithm for sequential decision processes
- Policy iteration accelerated with Krylov methods
This page was built for publication: Truncated policy iteration methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1060136)
