K-nearest Multi-agent Deep Reinforcement Learning for Collaborative Tasks with a Variable Number of Agents
This addresses a practical issue in industrial applications where agent availability fluctuates, though it appears incremental as it adapts existing methods to variable agent counts.
The paper tackles the problem of multi-agent deep reinforcement learning for collaborative tasks with a variable number of agents, proposing a new algorithm and demonstrating its application in a fleet management simulator with realistic production scenarios.
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.