Individual Regret in Cooperative Stochastic Multi-Armed Bandits

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Barnea, Idan, Lancewicki, Tal, Mansour, Yishay
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910009146736640
author Barnea, Idan
Lancewicki, Tal
Mansour, Yishay
author_facet Barnea, Idan
Lancewicki, Tal
Mansour, Yishay
contents We study the regret in stochastic Multi-Armed Bandits (MAB) with multiple agents that communicate over an arbitrary connected communication graph. We analyzed a variant of Cooperative Successive Elimination algorithm, COOP-SE, and show an individual regret bound of $O(R/ m + A^2 + A \sqrt{\log T})$ and a nearly matching lower bound. Here $A$ is the number of actions, $T$ the time horizon, $m$ the number of agents, and $R = \sum_{Δ_i > 0}\log(T)/Δ_i$ is the optimal single agent regret, where $Δ_i$ is the sub-optimality gap of action $i$. Our work is the first to show an individual regret bound in cooperative stochastic MAB that is independent of the graph's diameter. When considering communication networks there are additional considerations beyond regret, such as message size and number of communication rounds. First, we show that our regret bound holds even if we restrict the messages to be of logarithmic size. Second, for logarithmic number of communication rounds, we obtain a regret bound of $O(R / m+A \log T)$.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06501
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Individual Regret in Cooperative Stochastic Multi-Armed Bandits
Barnea, Idan
Lancewicki, Tal
Mansour, Yishay
Machine Learning
We study the regret in stochastic Multi-Armed Bandits (MAB) with multiple agents that communicate over an arbitrary connected communication graph. We analyzed a variant of Cooperative Successive Elimination algorithm, COOP-SE, and show an individual regret bound of $O(R/ m + A^2 + A \sqrt{\log T})$ and a nearly matching lower bound. Here $A$ is the number of actions, $T$ the time horizon, $m$ the number of agents, and $R = \sum_{Δ_i > 0}\log(T)/Δ_i$ is the optimal single agent regret, where $Δ_i$ is the sub-optimality gap of action $i$. Our work is the first to show an individual regret bound in cooperative stochastic MAB that is independent of the graph's diameter. When considering communication networks there are additional considerations beyond regret, such as message size and number of communication rounds. First, we show that our regret bound holds even if we restrict the messages to be of logarithmic size. Second, for logarithmic number of communication rounds, we obtain a regret bound of $O(R / m+A \log T)$.
title Individual Regret in Cooperative Stochastic Multi-Armed Bandits
topic Machine Learning
url https://arxiv.org/abs/2411.06501