On limitations of learning algorithms in competitive environments
Artificial Intelligence
2021-06-21 v2
Abstract
We discuss conceptual limitations of generic learning algorithms pursuing adversarial goals in competitive environments, and prove that they are subject to limitations that are analogous to the constraints on knowledge imposed by the famous theorems of G\"odel and Turing. These limitations are shown to be related to intransitivity, which is commonly present in competitive environments.
Cite
@article{arxiv.2011.12728,
title = {On limitations of learning algorithms in competitive environments},
author = {Alexander Y Klimenko and Dimitri A Klimenko},
journal= {arXiv preprint arXiv:2011.12728},
year = {2021}
}
Comments
8 pages, 1 figure