Principled Option Learning in Markov Decision Processes
Machine Learning
2018-02-01 v3 Machine Learning
Abstract
It is well known that options can make planning more efficient, among their many benefits. Thus far, algorithms for autonomously discovering a set of useful options were heuristic. Naturally, a principled way of finding a set of useful options may be more promising and insightful. In this paper we suggest a mathematical characterization of good sets of options using tools from information theory. This characterization enables us to find conditions for a set of options to be optimal and an algorithm that outputs a useful set of options and illustrate the proposed algorithm in simulation.
Cite
@article{arxiv.1609.05524,
title = {Principled Option Learning in Markov Decision Processes},
author = {Roy Fox and Michal Moshkovitz and Naftali Tishby},
journal= {arXiv preprint arXiv:1609.05524},
year = {2018}
}