The Power of Communication in a Distributed Multi-Agent System
arXiv:2111.15611
Abstract
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.
arXiv commentCooperative AI Workshop at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia
References in corpus (9)
- Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- A Survey and Critique of Multiagent Deep Reinforcement Learning
- The Communicative Multiagent Team Decision Problem: Analyzing Teamwork Theories and Models
- Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving
- Deep Reinforcement Learning meets Graph Neural Networks: exploring a routing optimization use case
- Emergence of Grounded Compositional Language in Multi-Agent Populations
- A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity
- On the Origin of Deep Learning
- Optimal algebraic Breadth-First Search for sparse graphs