Reproduce “GLo-MAPPO: Multi-Agent Deep Reinforcement Learning for Energy-Efficient UAV-Assisted LoRa Networks” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Abdullahi Isa Ahmed, Jamal Bentahar, El Mehdi Amhoud
GLo-MAPPO coordinates multiple UAV-based LoRa gateways as they serve sensor devices and return to charging stations. Each UAV learns movement, spreading-factor, and transmit-power choices using local observations, while a separate channel-gain rule assigns devices to eligible gateways. In simulation with 50 end devices, it achieves 397.59 Mbit/J versus 141.67 for MAA2C; this metric excludes UAV propulsion power.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.