Dynamic Collaborative Multi-Agent Reinforcement Learning Communication for Autonomous Drone Reforestation

Philipp Dominic Siedler

Keywords: Multi-Agent Reinforcement Learning, Graph Neural Network, Distributed Reinforcement Learning, Collaboration, Communication, Proximal Policy Optimization, Auto-Curricula, Open-endedness

TL;DR: Collaboration utilising a GNN communication layer as part of a distributed auto-curricula MARL system for open-ended autonomous drone based reforestation task

Abstract: We approach autonomous drone-based reforestation with a collaborative multi-agent reinforcement learning (MARL) setup. Agents can communicate as part of a dynamically changing network. We explore collaboration and communication on the back of a high-impact problem. Forests are the main resource to control rising CO2 conditions. Unfortunately, the global forest volume is decreasing at an unprecedented rate. Many areas are too large and hard to traverse to plant new trees. To efficiently cover as much area as possible, here we propose a Graph Neural Network (GNN) based communication mechanism that enables collaboration. Agents can share location information on areas needing reforestation, which increases viewed area and planted tree count. We compare our proposed communication mechanism with a multi-agent baseline without the ability to communicate. Results show how communication enables collaboration and increases collective performance, planting precision and the risk-taking propensity of individual agents.