Confidence-Based Curriculum Learning for Multi-Agent Path Finding

Titelangaben

Phan, Thomy ; Driscoll, Joseph ; Romberg, Justin ; Koenig, Sven:
Confidence-Based Curriculum Learning for Multi-Agent Path Finding.
In: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS '24). - Richland, SC : International Foundation for Autonomous Agents and Multiagent Systems , 2024 . - S. 1558-1566 . - (ACM Conferences )
ISBN 979-8-4007-0486-4
DOI: https://doi.org/10.5555/3635637.3663016

Volltext

Link zum Volltext (externe URL):

Weitere URLs

Angaben zu Projekten

Abstract

A wide range of real-world applications can be formulated as Multi-Agent Path Finding (MAPF) problem, where the goal is to find collision-free paths for multiple agents with individual start and goal locations. State-of-the-art MAPF solvers are mainly centralized and depend on global information, which limits their scalability and flexibility regarding changes or new maps that would require expensive replanning. Multi-agent reinforcement learning (MARL) offers an alternative way by learning decentralized policies that can generalize over a variety of maps. While there exist some prior works that attempt to connect both areas, the proposed techniques are heavily engineered and very complex due to the integration of many mechanisms that limit generality and are expensive to use. We argue that much simpler and general approaches are needed to bring the areas of MARL and MAPF closer together with significantly lower costs. In this paper, we propose Confidence-based Auto-Curriculum for Team Update Stability (CACTUS) as a lightweight MARL approach to MAPF. CACTUS defines a simple reverse curriculum scheme, where the goal of each agent is randomly placed within an allocation radius around the agent's start location. The allocation radius increases gradually as all agents improve, which is assessed by a confidence-based measure. We evaluate CACTUS in various maps of different sizes, obstacle densities, and numbers of agents. Our experiments demonstrate better performance and generalization capabilities than state-of-the-art MARL approaches with less than 600,000 trainable parameters, which is less than 5% of the neural network size of current MARL approaches to MAPF.