SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits

09/21/2018
by   Etienne Boursier, et al.
0

We consider the stochastic multiplayer multi-armed bandit problem, where several players pull arms simultaneously and a collision occurs if the same arm is pulled by more than one player; this is a standard model of cognitive radio networks. We construct a decentralized algorithm that achieves the same performances as a centralized one, if players are synchronized and observe their collisions. We actually construct a communication protocol between players by enforcing willingly collisions, allowing them to share their exploration. With a weaker feedback, when collisions are not observed, we still maintain some communication between players but at the cost of some extra multiplicative term in the regret. We also prove that the logarithmic growth of the regret is still achievable in the dynamic case where players are not synchronized with each other, thus preventing communication. Finally, we prove that if all players follow naively the celebrated UCB algorithm, the total regret grows linearly.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/28/2019

An Optimal Algorithm in Multiplayer Multi-Armed Bandits

The paper addresses the Multiplayer Multi-Armed Bandit (MMAB) problem, w...
research
04/28/2019

Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without

We consider the non-stochastic version of the (cooperative) multi-player...
research
11/08/2021

An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit

We study the problem of information sharing and cooperation in Multi-Pla...
research
12/09/2015

Multi-Player Bandits -- a Musical Chairs Approach

We consider a variant of the stochastic multi-armed bandit problem, wher...
research
02/04/2020

Selfish Robustness and Equilibria in Multi-Player Bandits

Motivated by cognitive radios, stochastic multi-player multi-armed bandi...
research
08/25/2018

Multiplayer bandits without observing collision information

We study multiplayer stochastic multi-armed bandit problems in which the...
research
02/29/2020

Decentralized Multi-player Multi-armed Bandits with No Collision Information

The decentralized stochastic multi-player multi-armed bandit (MP-MAB) pr...

Please sign up or login with your details

Forgot password? Click here to reset