In this paper, we are interested in optimal decisions in a partially observable Markov universe. Our viewpoint departs from the dynamic programming viewpoint: we are directly approximating an optimal strategic tree depending on the observation. This approximation is made by means of a parameterized probabilistic law. In this paper, a particular family of hidden Markov models, with input and output, is considered as a learning framework. A method for optimizing the parameters of these HMMs is proposed and applied. This optimization method is based on the cross-entropic principle.
Publié le : 2004-08-10
Classification:
MDP/POMDP,
Hierarchical HMM,
Cross-Entropy,
Bayesian Networks,
Optimal Control,
[MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC],
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG],
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
@article{hal-00002521,
author = {Dambreville, Frederic},
title = {Learning a Machine for the Decision in a Partially Observable Markov Universe},
journal = {HAL},
volume = {2004},
number = {0},
year = {2004},
language = {en},
url = {http://dml.mathdoc.fr/item/hal-00002521}
}
Dambreville, Frederic. Learning a Machine for the Decision in a Partially Observable Markov Universe. HAL, Tome 2004 (2004) no. 0, . http://gdmltest.u-ga.fr/item/hal-00002521/