K-nearest Multi-agent Deep Reinforcement Learning for Collaborative Tasks with a Variable Number of Agents

TL;DR

This paper introduces a novel deep reinforcement learning algorithm designed for multi-agent collaborative tasks that can adapt to a variable number of agents, addressing real-world industrial challenges.

Contribution

The paper presents a new algorithm capable of handling changing agent counts in multi-agent systems, validated through a realistic fleet management simulation.

Findings

Effective in scenarios with fluctuating agent numbers

Improves robustness of multi-agent collaboration

Demonstrated in a realistic industrial simulator

Abstract

Traditionally, the performance of multi-agent deep reinforcement learning algorithms are demonstrated and validated in gaming environments where we often have a fixed number of agents. In many industrial applications, the number of available agents can change at any given day and even when the number of agents is known ahead of time, it is common for an agent to break during the operation and become unavailable for a period of time. In this paper, we propose a new deep reinforcement learning algorithm for multi-agent collaborative tasks with a variable number of agents. We demonstrate the application of our algorithm using a fleet management simulator developed by Hitachi to generate realistic scenarios in a production site.