Application of LLMs to Multi-Robot Path Planning and Task Allocation

TL;DR

This paper explores using large-language models as expert planners to improve exploration efficiency in multi-agent reinforcement learning for path planning and task allocation.

Contribution

It introduces the novel idea of applying large-language models as expert planners in multi-agent exploration tasks, addressing the complexity of multi-agent reinforcement learning.

Findings

Large-language models can effectively guide exploration in multi-agent environments.

Using LLMs improves learning efficiency in multi-robot path planning.

The approach demonstrates potential for scalable multi-agent task coordination.

Abstract

Efficient exploration is a well known problem in deep reinforcement learning and this problem is exacerbated in multi-agent reinforcement learning due the intrinsic complexities of such algorithms. There are several approaches to efficiently explore an environment to learn to solve tasks by multi-agent operating in that environment, of which, the idea of expert exploration is investigated in this work. More specifically, this work investigates the application of large-language models as expert planners for efficient exploration in planning based tasks for multiple agents.