A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

07/07/2022
by   Jiafan He, et al.
6

We study federated contextual linear bandits, where M agents cooperate with each other to solve a global contextual linear bandit problem with the help of a central server. We consider the asynchronous setting, where all agents work independently and the communication between one agent and the server will not trigger other agents' communication. We propose a simple algorithm named based on the principle of optimism. We prove that the regret of is bounded by Õ(d√(∑_m=1^M T_m)) and the communication complexity is Õ(dM^2), where d is the dimension of the contextual vector and T_m is the total number of interactions with the environment by m-th agent. To the best of our knowledge, this is the first provably efficient algorithm that allows fully asynchronous communication for federated contextual linear bandits, while achieving the same regret guarantee as in the single-agent setting.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/10/2023

Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation

We study multi-agent reinforcement learning in the setting of episodic M...
research
05/26/2022

Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost

We study distributed contextual linear bandits with stochastic contexts,...
research
10/04/2021

Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits

Linear contextual bandit is a popular online learning problem. It has be...
research
03/29/2023

Federated Stochastic Bandit Learning with Unobserved Context

We study the problem of federated stochastic multi-arm contextual bandit...
research
11/03/2020

Federated LQR: Learning through Sharing

In many multi-agent reinforcement learning applications such as flocking...
research
09/21/2023

Incentivized Communication for Federated Bandits

Most existing works on federated bandits take it for granted that all cl...
research
06/10/2022

Communication Efficient Distributed Learning for Kernelized Contextual Bandits

We tackle the communication efficiency challenge of learning kernelized ...

Please sign up or login with your details

Forgot password? Click here to reset