[2I5-GS-10] AI application:

[2I5-GS-10-03] Efficient Assignment of Immediate Tasks Using Deep Reinforcement Learning in Multi-Agent Pickup and Delivery

〇Taisei Hirayama¹, Kohei Yoshida², Hiroki Sakaji¹, Itsuki Noda¹ (1. Hokkaido University, 2. Toyota Industries Corporation)

Keywords:Multi-Agent Pickup and Delivery (MAPD), Deep Reinforcement Learning, Task Assignment, Interruption

This paper first introduces Multi-Agent Pickup and Delivery with immediate tasks as MAPD-I.
While MAPD for the automated warehouses suppose that all delivery tasks are given at planning phases, there are several situations where the system needs to accept immediate and emergent tasks in real-time in practical applications.
Subsequently, we propose an efficiency improvement method using deep reinforcement learning for the acceptance of immediate tasks in automated warehouses.
Typical interrupt handling methods prioritize immediate tasks for rapid processing but do not consider the delays caused to regular tasks.
In this study, we aim to improve overall efficiency by moderately procrast the handling of interrupt tasks.
We propose a deep reinforcement learning model, ProcrastiNet, which determines the appropriate degree of procrastination, and compare its performance with typical interrupt handling methods and rule-based approach.