Learning a Machine for the Decision in a Partially Observable Markov Universe

2004/08/11 by Frédéric Dambreville, Dambreville, Frederic
Computer Science · #Algorithms and Data Compression #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Mathematics #General Mathematics (math.GM) #Machine Learning (cs.LG) #Machine Learning and Algorithms #Reinforcement Learning in Robotics

paper · doi:10.48550/arxiv.math/0408146

openalex publication_date 2004/08/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Related

• Cross-Entropic Learning of a Machine for the Decision in a Partially Observable Universe
• Information-Theoretic Methods for Planning and Learning in Partially Observable Markov Decision Processes
• Hidden Markov Model Estimation-Based Q-learning for Partially Observable\n Markov Decision Process
• Learning in Observable POMDPs, without Computationally Intractable Oracles
• Sequential Stochastic Optimization in Separable Learning Environments