Reinforcement learning from comparisons: Three alternatives is enough, two is not
Optimization and Control
2013-01-25 v1 Machine Learning
Probability
Abstract
The paper deals with the problem of finding the best alternatives on the basis of pairwise comparisons when these comparisons need not be transitive. In this setting, we study a reinforcement urn model. We prove convergence to the optimal solution when reinforcement of a winning alternative occurs each time after considering three random alternatives. The simpler process, which reinforces the winner of a random pair does not always converges: it may cycle.
Keywords
Cite
@article{arxiv.1301.5734,
title = {Reinforcement learning from comparisons: Three alternatives is enough, two is not},
author = {Benoit Laslier and Jean-Francois Laslier},
journal= {arXiv preprint arXiv:1301.5734},
year = {2013}
}