Multi-Agent Low-Dimensional Linear Bandits

07/02/2020
by   Ronshee Chawla, et al.
0

We study a multi-agent stochastic linear bandit with side information, parameterized by an unknown vector θ^* ∈ℝ^d. The side information consists of a finite collection of low-dimensional subspaces, one of which contains θ^*. In our setting, agents can collaborate to reduce regret by sending recommendations across a communication graph connecting them. We present a novel decentralized algorithm, where agents communicate subspace indices with each other, and each agent plays a projected variant of LinUCB on the corresponding (low-dimensional) subspace. Through a combination of collaborative best subspace identification, and per-agent learning of an unknown vector in the corresponding low-dimensional subspace, we show that the per-agent regret is much smaller than the case when agents do not communicate. By collaborating to identify the subspace containing θ^*, we show that each agent effectively solves an easier instance of the linear bandit (compared to the case of no collaboration), thus leading to the reduced per-agent regret. We finally complement these results through simulations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/12/2022

Collaborative Multi-agent Stochastic Linear Bandits

We study a collaborative multi-agent stochastic linear bandit setting, w...
research
10/04/2019

Social Learning in Multi Agent Multi Armed Bandits

In this paper, we introduce a distributed version of the classical stoch...
research
01/15/2020

The Gossiping Insert-Eliminate Algorithm for Multi-Agent Bandits

We consider a decentralized multi-agent Multi Armed Bandit (MAB) setup c...
research
11/02/2020

Stochastic Linear Bandits with Protected Subspace

We study a variant of the stochastic linear bandit problem wherein we op...
research
12/01/2020

Decentralized Multi-Agent Linear Bandits with Safety Constraints

We study decentralized stochastic linear bandits, where a network of N a...
research
06/26/2019

Orthogonal Projection in Linear Bandits

The expected reward in a linear stochastic bandit model is an unknown li...
research
09/15/2023

Clustered Multi-Agent Linear Bandits

We address in this paper a particular instance of the multi-agent linear...

Please sign up or login with your details

Forgot password? Click here to reset