Year: 2021
Type: preprint
Abstract: The information ratio offers an approach to assessing the efficacy with which an agent balances between exploration and exploitation. Originally, this was defined to be the ratio between squared expected regret and the mutual information between the environment and action-observation pair, which represents a measure of information gain. Recent work has inspired consideration of alternative information measures, particularly for use in analysis of bandit learning algorithms to arrive at tighter regret bounds. We investigate whether quantification of information via such alternatives can improve the realized performance of information-directed sampling, which aims to minimize the information ratio.
Source: arXiv (Cornell University)
Institution: Stanford University
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
Funder: Army Research Office
Award: G7566079004
OpenAlex ID: W3131850260