Collaborative Auto-Curricula Multi-Agent Reinforcement Learning with Graph Neural Network Communication Layer for Open-ended Wildfire-Management Resource Distribution

TL;DR

This paper introduces a multi-agent reinforcement learning system with a graph neural network communication layer, designed for wildfire resource distribution, demonstrating improved cooperation, generalizability, and performance over baselines.

Contribution

It proposes a novel MARL framework with auto-curricula and open-ended training, enhancing cooperation and generalizability in wildfire management tasks.

Findings

Outperforms baseline methods in resource distribution tasks.

Auto-curricula and open-ended training improve generalizability.

Communication via GNN enhances cooperative behavior.

Abstract

Most real-world domains can be formulated as multi-agent (MA) systems. Intentionality sharing agents can solve more complex tasks by collaborating, possibly in less time. True cooperative actions are beneficial for egoistic and collective reasons. However, teaching individual agents to sacrifice egoistic benefits for a better collective performance seems challenging. We build on a recently proposed Multi-Agent Reinforcement Learning (MARL) mechanism with a Graph Neural Network (GNN) communication layer. Rarely chosen communication actions were marginally beneficial. Here we propose a MARL system in which agents can help collaborators perform better while risking low individual performance. We conduct our study in the context of resource distribution for wildfire management. Communicating environmental features and partially observable fire occurrence help the agent collective to pre-emptively distribute resources. Furthermore, we introduce a procedural training environment accommodating auto-curricula and open-endedness towards better generalizability. Our MA communication proposal outperforms a Greedy Heuristic Baseline and a Single-Agent (SA) setup. We further demonstrate how auto-curricula and openendedness improves generalizability of our MA proposal.