When to Call Your Neighbor? Strategic Communication in Cooperative Stochastic Bandits

10/08/2021
by   Udari Madhushani, et al.
0

In cooperative bandits, a framework that captures essential features of collective sequential decision making, agents can minimize group regret, and thereby improve performance, by leveraging shared information. However, sharing information can be costly, which motivates developing policies that minimize group regret while also reducing the number of messages communicated by agents. Existing cooperative bandit algorithms obtain optimal performance when agents share information with their neighbors at every time step, i.e., full communication. This requires Θ(T) number of messages, where T is the time horizon of the decision making process. We propose ComEx, a novel cost-effective communication protocol in which the group achieves the same order of performance as full communication while communicating only O(log T) number of messages. Our key step is developing a method to identify and only communicate the information crucial to achieving optimal performance. Further we propose novel algorithms for several benchmark cooperative bandit frameworks and show that our algorithms obtain state-of-the-art performance while consistently incurring a significantly smaller communication cost than existing algorithms.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/21/2015

On Distributed Cooperative Decision-Making in Multiarmed Bandits

We study the explore-exploit tradeoff in distributed cooperative decisio...
research
04/13/2020

Distributed Learning: Sequential Decision Making in Resource-Constrained Environments

We study cost-effective communication strategies that can be used to imp...
research
05/27/2022

Private and Byzantine-Proof Cooperative Decision-Making

The cooperative bandit problem is a multi-agent decision problem involvi...
research
04/21/2019

Structural Self-adaptation for Decentralized Pervasive Intelligence

Communication structure plays a key role in the learning capability of d...
research
11/24/2021

One More Step Towards Reality: Cooperative Bandits with Imperfect Communication

The cooperative bandit problem is increasingly becoming relevant due to ...
research
02/15/2023

On-Demand Communication for Asynchronous Multi-Agent Bandits

This paper studies a cooperative multi-agent multi-armed stochastic band...
research
10/05/2020

An Efficient Algorithm for Cooperative Semi-Bandits

We consider the problem of asynchronous online combinatorial optimizatio...

Please sign up or login with your details

Forgot password? Click here to reset