Inference Strategies for Solving Semi-Markov Decision Processes
, 2012 Semi-Markov decision processes are used to formulate many control problems and also play a key role in hierarchical reinforcement learning. In this chapter we show how to translate the decision making problem into a form that can instead be solved by ...
Nando de Freitas, Matthew Hoffman
core +4 more sources
Mixed Markov Decision Processes in a Semi-Markov Environment with Discounted Criterion
Journal of Mathematical Analysis and Applications, 1998 This paper presents a new model: the mixed Markov decision process (MDP) in a semi-Markov environment with discounted criterion. It describes a system which behaves like a MDP except that the system is influenced by its semi-Markov process environment ...
Hu, Qiying, Wang, Jinling
core +2 more sources
Risk probability optimization problem for finite horizon continuous time Markov decision processes with loss rate [PDF]
, 2021 summary:This paper presents a study the risk probability optimality for finite horizon continuous-time Markov decision process with loss rate and unbounded transition rates.
Wen, Xian, Huo, Haifeng
core +1 more source
The exponential cost optimality for finite horizon semi-Markov decision processes [PDF]
, 2022 summary:This paper considers an exponential cost optimality problem for finite horizon semi-Markov decision processes (SMDPs). The objective is to calculate an optimal policy with minimal exponential costs over the full set of policies in a finite ...
Wen, Xian, Huo, Haifeng
core +1 more source
A Hemimetric Extension of Simulation for Semi-Markov Decision Processes [PDF]
, 2018 Semi-Markov decision processes (SMDPs) are continuous-time Markov decision processes where the residence-time on states is governed by generic distributions on the positive real line. In this paper we consider the problem of comparing two SMDPs with respect to their time-dependent behaviour.
Mathias Ruggaard Pedersen +3 more
openaire +5 more sources
A survey on semi-Markov decision processes [PDF]
SCIENTIA SINICA Mathematica, 2015 This paper is a survey on semi-Markov decision processes (SMDPs). We present the background, the signi cance, and the research actuality of the in nite horizon expected discounted reward criterion, the long-run expected average reward criterion, the nite horizon expected reward criterion, the expected rst passage reward criterion, the probability ...
YongHui HUANG, XianPing GUO
openaire +1 more source
Recursive Markov Decision Processes and Recursive Stochastic Games [PDF]
, 2005 We introduce Recursive Markov Decision Processes (RMDPs) and Recursive Simple Stochastic Games (RSSGs), and study the decidability and complexity of algorithms for their analysis and verification.
Mihalis Yannakakis +3 more
core +1 more source
Symbolic Magnifying Lens Abstraction in Markov Decision Processes [PDF]
, 2008 In this paper, we combine abstraction-refinement and symbolic techniques to fight the state-space explosion problem when model checking Markov decision processes (MDPs).
Luca de Alfaro +7 more
core +1 more source
Efficient qualitative analysis of classes of recursive markov decision processes and simple stochastic games [PDF]
, 2006 . Recursive Markov Decision Processes (RMDPs) and Recursive Simple Stochastic Games (RSSGs) are natural models for recursive systems involving both probabilistic and non-probabilistic actions.
Mihalis Yannakakis +3 more
core +1 more source
Towards Analysis of Semi-Markov Decision Processes [PDF]
, 2010 We investigate Semi-Markov Decision Processes (SMDPs). Two problems are studied, namely, the time-bounded reachability problem and the long-run average fraction of time problem. The former aims to compute the maximal (or minimum) probability to reach a certain set of states within a given time bound.
Taolue Chen 0001, Jian Lu 0001
openaire +1 more source