When are Kalman-filter restless bandits indexable?
Machine Learning
2015-09-16 v1
Abstract
We study the restless bandit associated with an extremely simple scalar Kalman filter model in discrete time. Under certain assumptions, we prove that the problem is indexable in the sense that the Whittle index is a non-decreasing function of the relevant belief state. In spite of the long history of this problem, this appears to be the first such proof. We use results about Schur-convexity and mechanical words, which are particular binary strings intimately related to palindromes.
Cite
@article{arxiv.1509.04541,
title = {When are Kalman-filter restless bandits indexable?},
author = {Christopher R. Dance and Tomi Silander},
journal= {arXiv preprint arXiv:1509.04541},
year = {2015}
}
Comments
To appear in NIPS 2015