2021/11/30 by Philipp Dominic Siedler, Siedler, Philipp Dominic
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #cs.AI #cs.LG #cs.MA
paper · pdf · doi:10.48550/arxiv.2111.15611
Cooperative AI Workshop at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia
arxiv created 2021/12/14 · arxiv updated 2021/12/16
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.