Multi-Player Bandits Robust to Adversarial Collisions

11/15/2022
by   Shivakumar Mahesh, et al.
0

Motivated by cognitive radios, stochastic Multi-Player Multi-Armed Bandits has been extensively studied in recent years. In this setting, each player pulls an arm, and receives a reward corresponding to the arm if there is no collision, namely the arm was selected by one single player. Otherwise, the player receives no reward if collision occurs. In this paper, we consider the presence of malicious players (or attackers) who obstruct the cooperative players (or defenders) from maximizing their rewards, by deliberately colliding with them. We provide the first decentralized and robust algorithm RESYNC for defenders whose performance deteriorates gracefully as Õ(C) as the number of collisions C from the attackers increases. We show that this algorithm is order-optimal by proving a lower bound which scales as Ω(C). This algorithm is agnostic to the algorithm used by the attackers and agnostic to the number of collisions C faced from attackers.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/28/2022

Multi-Player Multi-Armed Bandits with Finite Shareable Resources Arms: Learning Algorithms Applications

Multi-player multi-armed bandits (MMAB) study how decentralized players ...
research
02/04/2020

Selfish Robustness and Equilibria in Multi-Player Bandits

Motivated by cognitive radios, stochastic multi-player multi-armed bandi...
research
11/05/2018

Multi-armed Bandits with Compensation

We propose and study the known-compensation multi-arm bandit (KCMAB) pro...
research
06/25/2021

Multi-player Multi-armed Bandits with Collision-Dependent Reward Distributions

We study a new stochastic multi-player multi-armed bandits (MP-MAB) prob...
research
03/24/2021

Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Information

We propose a novel algorithm for multi-player multi-armed bandits withou...
research
11/07/2017

Multi-Player Bandits Models Revisited

Multi-player Multi-Armed Bandits (MAB) have been extensively studied in ...
research
12/22/2021

IDCAIS: Inter-Defender Collision-Aware Interception Strategy against Multiple Attackers

This paper presents an Inter-Defender Collision-Aware Interception Strat...

Please sign up or login with your details

Forgot password? Click here to reset