Results 51 to 60 of about 9,481,834 (176)

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, VOL. 42, NO. 12, DECEMBER 1997 1663 The Policy Iteration Algorithm for Average Reward

, 2007
The average cost optimal control problem is addressed for Markov decision processes with unbounded cost. It is found that the policy iteration algorithm generates a sequence of policies which are (a strong stability condition), where c is the cost ...
Markov Decision Processes
core  

Introduction

, 2017
This book is devoted to the study of asymptotic expansions for moment of hitting times, stationary and conditional quasi-stationary distributions, and other functionals, for nonlinearly perturbed semi-Markov processes. The introduction intends to present
Sergei Silvestrov, Silvestrov, Sergei,, Silvestrov, D.,, Dmitrii Silvestrov   +3 more
core   +1 more source

The semi-Markov beta-Stacy process: a Bayesian non-parametric prior for semi-Markov processes

, 2020
The literature on Bayesian methods for the analysis of discrete-time semi-Markov processes is sparse. In this paper, we introduce the semi-Markov beta-Stacy process, a stochastic process useful for the Bayesian non-parametric analysis of semi-Markov ...
Peluso S.
core   +1 more source

Nonstationary Continuous Time Markov Decision Processes in a Semi-Markov Environment with Discounted Criterion [PDF]

, 1995
This paper deals with the nonstationary continuous time Markov decision process in a semi-Markov environment with discounted criterion. The model can describe a system that itself can be modeled by a countable state nonstationary continuous time Markov ...
Hu, Q.Y.
core   +1 more source

A Passage-time Preserving Equivalence for

, 2002
An equivalence for semi-Markov processes is presented which preserves passage-time distributions between pairs of states in a given set. The equivalence is based upon a state-based aggregation procedure which is O(n ) per state in the worst ...
Semi-Markov Processes Bradley
core  

Solving Hidden-Semi-Markov-Mode Markov Decision Problems

, 2014
International audienceHidden-Mode Markov Decision Processes (HM-MDPs) were proposed to represent sequential decision-making problems in non-stationary environments that evolve according to a Markov chain.
Hadoux, Emmanuel, Beynier, Aurélie, Weng, Paul   +2 more
core   +2 more sources

Hidden Semi Markov Models for Multiple Observation Sequences: The mhsmm Package for R [PDF]

This paper describes the R package mhsmm which implements estimation and prediction methods for hidden Markov and semi-Markov models for multiple observation sequences. Such techniques are of interest when observed data is thought to be dependent on some
Søren Højsgaard, Jared O'Connell
core  

Regret based Robust Solutions for Uncertain Markov Decision Processes [PDF]

, 2013
In this paper, we seek robust policies for uncertain Markov Decision Processes (MDPs). Most robust optimization approaches for these problems have focussed on the computation of {\em maximin} policies which maximize the value corresponding to the worst ...
Varakantham, Pradeep, Yossiri Adulyasak, Adulyasak, Yossiri, AHMED, Asrar, Jaillet, Patrick, Patrick Jaillet, Asrar Ahmed, Pradeep Varakantham, VARAKANTHAM, Pradeep Reddy   +8 more
core  

Second Order Optimality in Markov and Semi-Markov Decision Processes

, 2019
Semi-Markov decision processes can be considered as an extension of discrete- and continuous-time Markov reward models. Unfortunately, traditional optimality criteria as long-run average reward per time may be quite insufficient to characterize the ...
Sladký, Karel
core  

The existence and characterisation of duality of Markov processes in the Euclidean space [PDF]

This thesis examines the existence of dualMarkov processes and presents the full characterization of Markov processes in Euclidean space equipped with the natural order (the Pareto order).
Lee, Rui Xin
core