Application of LLMs to Multi-Robot Path Planning and Task Allocation
This addresses exploration challenges in multi-agent systems, which is an incremental improvement over existing expert exploration methods.
The paper tackles the problem of inefficient exploration in multi-agent reinforcement learning by using large-language models as expert planners for multi-robot path planning and task allocation, resulting in improved exploration efficiency.
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.