The Power of Communication in a Distributed Multi-Agent System
This work addresses the challenge of scaling and optimizing distributed multi-agent systems for real-world applications like renewable energy, though it appears incremental by combining existing methods.
The paper tackles the problem of improving efficiency and reducing training time in multi-agent reinforcement learning systems by introducing a communication mechanism based on Dec-POMDPs and GNNs, applied to an offshore wind farm scenario, resulting in significantly reduced training time and higher cumulative rewards compared to single-agent systems.
Single-Agent (SA) Reinforcement Learning systems have shown outstanding re-sults on non-stationary problems. However, Multi-Agent Reinforcement Learning(MARL) can surpass SA systems generally and when scaling. Furthermore, MAsystems can be super-powered by collaboration, which can happen through ob-serving others, or a communication system used to share information betweencollaborators. Here, we developed a distributed MA learning mechanism withthe ability to communicate based on decentralised partially observable Markovdecision processes (Dec-POMDPs) and Graph Neural Networks (GNNs). Minimis-ing the time and energy consumed by training Machine Learning models whileimproving performance can be achieved by collaborative MA mechanisms. Wedemonstrate this in a real-world scenario, an offshore wind farm, including a set ofdistributed wind turbines, where the objective is to maximise collective efficiency.Compared to a SA system, MA collaboration has shown significantly reducedtraining time and higher cumulative rewards in unseen and scaled scenarios.