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

TL;DR

This paper extends mean field game analysis to multi-armed bandit problems with continuous rewards, establishing existence and uniqueness of equilibrium, and demonstrating practical effectiveness through evaluations.

Contribution

It introduces a novel mean field model for multi-agent bandits with continuous rewards, proving equilibrium existence and uniqueness, and transforming stochastic dynamics into a deterministic ODE for analysis.

Findings

Existence of mean field equilibrium established.

Uniqueness of equilibrium guaranteed via contraction mapping.

Empirical results show tight regret bounds.

Abstract

Mean field game facilitates analyzing multi-armed bandit (MAB) for a large number of agents by approximating their interactions with an average effect. Existing mean field models for multi-agent MAB mostly assume a binary reward function, which leads to tractable analysis but is usually not applicable in practical scenarios. In this paper, we study the mean field bandit game with a continuous reward function. Specifically, we focus on deriving the existence and uniqueness of mean field equilibrium (MFE), thereby guaranteeing the asymptotic stability of the multi-agent system. To accommodate the continuous reward function, we encode the learned reward into an agent state, which is in turn mapped to its stochastic arm playing policy and updated using realized observations. We show that the state evolution is upper semi-continuous, based on which the existence of MFE is obtained. As the Markov analysis is mainly for the case of discrete state, we transform the stochastic continuous state evolution into a deterministic ordinary differential equation (ODE). On this basis, we can characterize a contraction mapping for the ODE to ensure a unique MFE for the bandit game. Extensive evaluations validate our MFE characterization, and exhibit tight empirical regret of the MAB problem.