Anzeige
Erschienen in:
2020 | OriginalPaper | Buchkapitel
Learning to Communicate with Multi-agent Reinforcement Learning Using Value-Decomposition Networks
verfasst von : Simon Vanneste, Astrid Vanneste, Stig Bosmans, Siegfried Mercelis, Peter Hellinckx
Erschienen in: Advances on P2P, Parallel, Grid, Cloud and Internet Computing
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
Recent research focuses on how agents can learn to communicate with each other. This communication between the agents allows them to share information and coordinate their behaviour. Recent efforts have proven successful in these cooperative problems. A major problem we face in multi-agent reinforcement learning is the lazy agent problem, where some agents take advantage of the successful actions of other agents. This results in agents not being able to learn a functional policy. In this paper we will combine state-of-the-art methods to design an architecture to address cooperative problems using communication while also eliminating the lazy agent problem. We propose two approaches for learning to communicate that use value decomposition to address the lazy agent problem. We find that the additive version of value decomposition gives us results which exceeds the results of the state of the art.