Fair Algorithms for Multi-Agent Multi-Armed Bandits

07/13/2020
by   Safwan Hossain, et al.
0

We propose a multi-agent variant of the classical multi-armed bandit problem, in which there are N agents and K arms, and pulling an arm generates a (possibly different) stochastic reward to each agent. Unlike the classical multi-armed bandit problem, the goal is not to learn the "best arm", as each agent may perceive a different arm as best for her. Instead, we seek to learn a fair distribution over arms. Drawing on a long line of research in economics and computer science, we use the Nash social welfare as our notion of fairness. We design multi-agent variants of three classic multi-armed bandit algorithms, and show that they achieve sublinear regret, now measured in terms of the Nash social welfare.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/23/2022

An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regret

Recently a multi-agent variant of the classical multi-armed bandit was p...
research
10/23/2021

Multi-armed Bandit Algorithm against Strategic Replication

We consider a multi-armed bandit problem in which a set of arms is regis...
research
05/27/2022

Fairness and Welfare Quantification for Regret in Multi-Armed Bandits

We extend the notion of regret with a welfarist perspective. Focussing o...
research
11/05/2019

Response Prediction for Low-Regret Agents

Companies like Google and Microsoft run billions of auctions every day t...
research
02/27/2020

Online Learning for Active Cache Synchronization

Existing multi-armed bandit (MAB) models make two implicit assumptions: ...
research
09/14/2018

Dueling Bandits with Qualitative Feedback

We formulate and study a novel multi-armed bandit problem called the qua...
research
05/03/2021

Mean Field Equilibrium in Multi-Armed Bandit Game with Continuous Reward

Mean field game facilitates analyzing multi-armed bandit (MAB) for a lar...

Please sign up or login with your details

Forgot password? Click here to reset