Tag
This paper introduces PLATO, a pointer-network-based actor with a graph neural network critic for multi-agent reinforcement learning that handles both agent and task openness without retraining, evaluated in a wildfire suppression domain.
Firefighting drones capable of spraying water and retardants are being tested in California and Alaska, including autonomous swarms from Seneca, to provide rapid response to wildfires exacerbated by climate change.