Log In Sign Up

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

by   Philipp Dominic Siedler, et al.

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.


page 1

page 6

page 7

page 27

page 28

page 29

page 30

page 31


Learning to Gather without Communication

A standard belief on emerging collective behavior is that it emerges fro...

The Power of Communication in a Distributed Multi-Agent System

Single-Agent (SA) Reinforcement Learning systems have shown outstanding ...

Universally Expressive Communication in Multi-Agent Reinforcement Learning

Allowing agents to share information through communication is crucial fo...

Collective Iterative Learning Control: Exploiting Diversity in Multi-Agent Systems for Reference Tracking Tasks

This paper considers a group of autonomous agents learning to track the ...

Programming and Deployment of Autonomous Swarms using Multi-Agent Reinforcement Learning

Autonomous systems (AS) carry out complex missions by continuously obser...