87 search results - page 3 / 18 » A policy iteration algorithm for Markov decision processes s... |
CORR
2012
Springer
12 years 3 months ago
2012
Springer
Abstract— In this paper, we consider a class of continuoustime, continuous-space stochastic optimal control problems. Building upon recent advances in Markov chain approximation ...
IJCAI
2007
13 years 9 months ago
2007
Agents often have to construct plans that obey deadlines or, more generally, resource limits for real-valued resources whose consumption can only be characterized by probability d...
JMLR
2002
13 years 7 months ago
2002
We consider a finite-state Markov decision problem and establish the convergence of a special case of optimistic policy iteration that involves Monte Carlo estimation of Q-values,...
AAAI
1997
13 years 8 months ago
1997
Many stochastic planning problems can be represented using Markov Decision Processes (MDPs). A difficulty with using these MDP representations is that the common algorithms for so...
ECSQARU
2001
Springer
13 years 12 months ago
2001
Springer
Abstract. Finding optimal policies for general partially observable Markov decision processes (POMDPs) is computationally difficult primarily due to the need to perform dynamic-pr...