Cooperative learning in multi-agent systems from intermittent measurements
This addresses decentralized tracking and learning in multi-agent systems, but appears incremental as it builds on existing distributed learning frameworks.
The paper tackles the problem of cooperative learning of an unknown vector from noisy, intermittent measurements in multi-agent systems with time-varying connectivity, proposing a distributed protocol that bounds learning speed based on network size and combinatorial features.
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 $μ$ 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 $μ$. 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.