Multi Agent Path Finding using Evolutionary Game Theory

TL;DR

This paper introduces a novel multi-agent pathfinding approach using evolutionary game theory, outperforming existing reinforcement learning methods in efficiency, scalability, and stability in unknown stochastic environments.

Contribution

It applies evolutionary game theory to multi-agent pathfinding, demonstrating superior performance and stability over traditional RL algorithms in complex environments.

Findings

Achieves nearly 30% shorter path lengths than state-of-the-art RL methods.

Runs at least ten times faster than deep RL algorithms.

Scales better with increasing number of agents.

Abstract

In this paper, we consider the problem of path finding for a set of homogeneous and autonomous agents navigating a previously unknown stochastic environment. In our problem setting, each agent attempts to maximize a given utility function while respecting safety properties. Our solution is based on ideas from evolutionary game theory, namely replicating policies that perform well and diminishing ones that do not. We do a comprehensive comparison with related multiagent planning methods, and show that our technique beats state of the art RL algorithms in minimizing path length by nearly 30% in large spaces. We show that our algorithm is computationally faster than deep RL methods by at least an order of magnitude. We also show that it scales better with an increase in the number of agents as compared to other methods, path planning methods in particular. Lastly, we empirically prove that the policies that we learn are evolutionarily stable and thus impervious to invasion by any other policy.