This paper is concerned with the links between the Value Iteration algorithm and the Rolling Horizon procedure, for solving problems of stochastic optimal control under the long-run average criterion, in Markov Decision Processes with finite state and action spaces. We review conditions of the literature which imply the geometric convergence of Value Iteration to the optimal value. Aperiodicity is an essential prerequisite for convergence. We prove that the convergence of Value Iteration generally implies that of Rolling Horizon. We also present a modified Rolling Horizon procedure that can be applied to models without analyzing periodicity, and discuss the impact of this transformation on convergence. We illustrate with numerous examples t...
This paper investigates the limit behavior of Markov Decision Processes (MDPs) made of independent p...
Value iteration is a fundamental algorithm for solving Markov Decision Processes (MDPs). It computes...
Bandits are one of the most basic examples of decision-making with uncertainty. A Markovian restless...
This paper is concerned with the links between the Value Iteration algorithm and the Rolling Horizon...
We study the properties of the rolling horizon and the approximate rolling horizon procedures for th...
International audienceWe deal with the average criterion on Markov Decision Processes (MDP) to evalu...
We consider the problem of approximating the values and the optimal policies in risk-averse discount...
Evolution Strategies (ESs) are population-based methods well suited for parallelization. In this rep...
We investigate the potential of the Markov decision processes theory through two applications. The f...
International audienceMarkov Decision Processes (MDP) are a widely used model including both non-det...
In this paper we propose the combination of accelerated variants of value iteration mixed with impro...
We consider problems that involve the sequential selection of decisions in order to minimize expecte...
We consider the problem of approximating the values and the optimal policies in risk-averse discount...
International audienceWe consider the infinite-horizon discounted optimal control problem formalized...
We give a policy iteration algorithm to solve zero-sum stochastic games with finite state and action...
This paper investigates the limit behavior of Markov Decision Processes (MDPs) made of independent p...
Value iteration is a fundamental algorithm for solving Markov Decision Processes (MDPs). It computes...
Bandits are one of the most basic examples of decision-making with uncertainty. A Markovian restless...
This paper is concerned with the links between the Value Iteration algorithm and the Rolling Horizon...
We study the properties of the rolling horizon and the approximate rolling horizon procedures for th...
International audienceWe deal with the average criterion on Markov Decision Processes (MDP) to evalu...
We consider the problem of approximating the values and the optimal policies in risk-averse discount...
Evolution Strategies (ESs) are population-based methods well suited for parallelization. In this rep...
We investigate the potential of the Markov decision processes theory through two applications. The f...
International audienceMarkov Decision Processes (MDP) are a widely used model including both non-det...
In this paper we propose the combination of accelerated variants of value iteration mixed with impro...
We consider problems that involve the sequential selection of decisions in order to minimize expecte...
We consider the problem of approximating the values and the optimal policies in risk-averse discount...
International audienceWe consider the infinite-horizon discounted optimal control problem formalized...
We give a policy iteration algorithm to solve zero-sum stochastic games with finite state and action...
This paper investigates the limit behavior of Markov Decision Processes (MDPs) made of independent p...
Value iteration is a fundamental algorithm for solving Markov Decision Processes (MDPs). It computes...
Bandits are one of the most basic examples of decision-making with uncertainty. A Markovian restless...