Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications
Machine Learning
2023-11-15 v2 Machine Learning
Abstract
Partial monitoring is an expressive framework for sequential decision-making with an abundance of applications, including graph-structured and dueling bandits, dynamic pricing and transductive feedback models. We survey and extend recent results on the linear formulation of partial monitoring that naturally generalizes the standard linear bandit setting. The main result is that a single algorithm, information-directed sampling (IDS), is (nearly) worst-case rate optimal in all finite-action games. We present a simple and unified analysis of stochastic partial monitoring, and further extend the model to the contextual and kernelized setting.
Cite
@article{arxiv.2302.03683,
title = {Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications},
author = {Johannes Kirschner and Tor Lattimore and Andreas Krause},
journal= {arXiv preprint arXiv:2302.03683},
year = {2023}
}