Linear Partial Monitoring for Sequential Decision Making: Algorithms, Regret Bounds and Applications
![Thumbnail](/bitstream/handle/20.500.11850/661344/22-1248.pdf.jpg?sequence=5&isAllowed=y)
Open access
Date
2023Type
- Journal Article
ETH Bibliography
yes
Altmetrics
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. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000661344Publication status
publishedExternal links
Journal / series
Journal of Machine Learning ResearchVolume
Pages / Article No.
Publisher
Microtome PublishingSubject
Sequential Decision-Making; Linear Partial Monitoring; Information-Directed Sampling; Linear BanditsFunding
815943 - Reliable Data-Driven Decision Making in Cyber-Physical Systems (EC)
More
Show all metadata
ETH Bibliography
yes
Altmetrics