Multi-agent navigation based on deep reinforcement learning and traditional pathfinding algorithm

TL;DR

This paper introduces a hybrid multi-agent navigation framework combining traditional pathfinding and deep reinforcement learning, enabling agents to effectively avoid collisions and reach targets in complex, large-scale environments.

Contribution

It presents a novel integration of pathfinding algorithms with reinforcement learning for multi-agent collision avoidance, adaptable to various scenarios and scales.

Findings

Agents successfully navigate to targets in complex scenarios

The framework adapts well to different environments and scales

Parameter tuning improves agent behavior

Abstract

We develop a new framework for multi-agent collision avoidance problem. The framework combined traditional pathfinding algorithm and reinforcement learning. In our approach, the agents learn whether to be navigated or to take simple actions to avoid their partners via a deep neural network trained by reinforcement learning at each time step. This framework makes it possible for agents to arrive terminal points in abstract new scenarios. In our experiments, we use Unity3D and Tensorflow to build the model and environment for our scenarios. We analyze the results and modify the parameters to approach a well-behaved strategy for our agents. Our strategy could be attached in different environments under different cases, especially when the scale is large.