Minimizing the Outage Probability in a Markov Decision Process
Machine Learning
2023-03-06 v2
Abstract
Standard Markov decision process (MDP) and reinforcement learning algorithms optimize the policy with respect to the expected gain. We propose an algorithm which enables to optimize an alternative objective: the probability that the gain is greater than a given value. The algorithm can be seen as an extension of the value iteration algorithm. We also show how the proposed algorithm could be generalized to use neural networks, similarly to the deep Q learning extension of Q learning.
Cite
@article{arxiv.2302.14714,
title = {Minimizing the Outage Probability in a Markov Decision Process},
author = {Vincent Corlay and Jean-Christophe Sibel},
journal= {arXiv preprint arXiv:2302.14714},
year = {2023}
}
Comments
Accepted at the Information Theory Workshop (ITW) 2023