Multi-Agent Path Planning Using Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning approach for multi-agent path planning, demonstrating that the trained model can quickly solve unseen routing problems with high efficiency in simulation.

Contribution

The paper presents a novel deep reinforcement learning method for multi-agent path planning that learns to solve routing problems efficiently without additional training.

Findings

Model's performance improves with experience in simulation.

Trained model can solve unseen problems instantly.

Proposed method outperforms traditional heuristics in computational speed.

Abstract

In this paper a deep reinforcement based multi-agent path planning approach is introduced. The experiments are realized in a simulation environment and in this environment different multi-agent path planning problems are produced. The produced problems are actually similar to a vehicle routing problem and they are solved using multi-agent deep reinforcement learning. In the simulation environment, the model is trained on different consecutive problems in this way and, as the time passes, it is observed that the model's performance to solve a problem increases. Always the same simulation environment is used and only the location of target points for the agents to visit is changed. This contributes the model to learn its environment and the right attitude against a problem as the episodes pass. At the end, a model who has already learned a lot to solve a path planning or routing problem in this environment is obtained and this model can already find a nice and instant solution to a given unseen problem even without any training. In routing problems, standard mathematical modeling or heuristics seem to suffer from high computational time to find the solution and it is also difficult and critical to find an instant solution. In this paper a new solution method against these points is proposed and its efficiency is proven experimentally.