Yi, Jialin and Vojnović, Milan 
ORCID: 0000-0003-1382-022X
(2023)
On regret-optimal cooperative nonstochastic multi-armed bandits.
Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, 2023-M.
pp. 1329-1335.
ISSN 1548-8403
Abstract
We consider the nonstochastic multi-agent multi-armed bandit problem with agents collaborating via a communication network with delays. We show a lower bound for individual regret of all agents. We show that with suitable regularizers and communication protocols, a collaborative multi-agent follow-the-regularized-leader (FTRL) algorithm has an individual regret upper bound that matches the lower bound up to a constant factor when the number of arms is large enough relative to degrees of agents in the communication graph. We also show that an FTRL algorithm with a suitable regularizer is regret optimal with respect to the scaling with the edge-delay parameter. We present numerical experiments validating our theoretical results and demonstrate cases when our algorithms outperform previously proposed algorithms.
| Item Type: | Article |
|---|---|
| Additional Information: | © 2023 International Foundation for Autonomous Agents and Multiagent Systems |
| Divisions: | LSE Statistics |
| Subjects: | H Social Sciences > HA Statistics Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Date Deposited: | 24 May 2024 11:36 |
| Last Modified: | 20 Dec 2024 00:54 |
| URI: | http://eprints.lse.ac.uk/id/eprint/123623 |
Actions (login required)
 |
View Item |
