A Bit Better? Quantifying Information for Bandit Learning
This work addresses a theoretical bottleneck in bandit algorithms for researchers, but it appears incremental as it builds on existing information ratio concepts.
The paper investigates whether alternative information measures can improve the performance of information-directed sampling in bandit learning, aiming to tighten regret bounds and enhance the balance between exploration and exploitation.
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.