Decentralized Age-of-Information Bandits
Archiki Prasad, Vishal Jain, Sharayu Moharir

TL;DR
This paper addresses the challenge of scheduling multiple data sources over multiple channels to minimize Age-of-Information (AoI) using multi-armed bandit algorithms, proposing new policies with performance guarantees.
Contribution
It introduces novel AoI-aware policies based on UCB and Thompson Sampling for distributed multi-armed bandit problems with unknown channel statistics.
Findings
Proven performance guarantees for UCB-based policy
Development of a Thompson Sampling-based policy
Simulation results showing improved AoI performance
Abstract
Age-of-Information (AoI) is a performance metric for scheduling systems that measures the freshness of the data available at the intended destination. AoI is formally defined as the time elapsed since the destination received the recent most update from the source. We consider the problem of scheduling to minimize the cumulative AoI in a multi-source multi-channel setting. Our focus is on the setting where channel statistics are unknown and we model the problem as a distributed multi-armed bandit problem. For an appropriately defined AoI regret metric, we provide analytical performance guarantees of an existing UCB-based policy for the distributed multi-armed bandit problem. In addition, we propose a novel policy based on Thomson Sampling and a hybrid policy that tries to balance the trade-off between the aforementioned policies. Further, we develop AoI-aware variants of these policies…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
