Cooperative learning in multi-agent systems from intermittent measurements

TL;DR

This paper introduces a distributed cooperative learning protocol for multi-agent systems that can learn an unknown vector despite intermittent, noisy measurements and changing network connectivity, with performance bounds based on network features.

Contribution

The paper presents a novel distributed learning protocol that handles intermittent measurements and dynamic network connectivity in multi-agent systems.

Findings

Protocol effectively learns the unknown vector in noisy, intermittent conditions.

Learning speed is bounded by network size and connectivity features.

Method is robust to time-varying, unpredictable communication patterns.

Abstract

Motivated by the problem of tracking a direction in a decentralized way, we consider the general problem of cooperative learning in multi-agent systems with time-varying connectivity and intermittent measurements. We propose a distributed learning protocol capable of learning an unknown vector $\mu$ from noisy measurements made independently by autonomous nodes. Our protocol is completely distributed and able to cope with the time-varying, unpredictable, and noisy nature of inter-agent communication, and intermittent noisy measurements of $\mu$. Our main result bounds the learning speed of our protocol in terms of the size and combinatorial features of the (time-varying) networks connecting the nodes.