Reinforcement Learning: a Comparison of UCB Versus Alternative Adaptive Policies
Machine Learning
2019-09-16 v1 Artificial Intelligence
Machine Learning
Abstract
In this paper we consider the basic version of Reinforcement Learning (RL) that involves computing optimal data driven (adaptive) policies for Markovian decision process with unknown transition probabilities. We provide a brief survey of the state of the art of the area and we compare the performance of the classic UCB policy of \cc{bkmdp97} with a new policy developed herein which we call MDP-Deterministic Minimum Empirical Divergence (MDP-DMED), and a method based on Posterior sampling (MDP-PS).
Keywords
Cite
@article{arxiv.1909.06019,
title = {Reinforcement Learning: a Comparison of UCB Versus Alternative Adaptive Policies},
author = {Wesley Cowan and Michael N. Katehakis and Daniel Pirutinsky},
journal= {arXiv preprint arXiv:1909.06019},
year = {2019}
}