Dynamic Collaborative Multi-Agent Reinforcement Learning Communication for Autonomous Drone Reforestation
This addresses the problem of large-scale reforestation for environmental sustainability, but it is incremental as it builds on existing MARL and GNN methods.
The paper tackles autonomous drone-based reforestation by proposing a Graph Neural Network (GNN) based communication mechanism for collaborative multi-agent reinforcement learning, which increases viewed area and planted tree count compared to a baseline without communication.
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.