ClusterComm: Discrete Communication in Decentralized MARL Using Internal Representation Clustering

Müller, Robert ; Turalic, Hasan; Phan, Thomy; Kölle, Michael; Nüßlein, Jonas und Linnhoff-Popien, Claudia (2024): ClusterComm: Discrete Communication in Decentralized MARL Using Internal Representation Clustering. ICAART 2024: International Conference on Agents and Artificial Intelligence, Rome, Italy, 24. Februar 2024 - 26. Februar 2024. Rocha, Ana Paula; Steels, Luc und Herik, Jaap van den (Hrsg.): In: Proceedings of the 16th International Conference on Agents and Artificial Intelligence, Bd. 1 Setúbal: SciTePress. S. 305-312

Abstract

In the realm of Multi-Agent Reinforcement Learning (MARL), prevailing approaches exhibit shortcomings in aligning with human learning, robustness, and scalability. Addressing this, we introduce ClusterComm, a fully decentralized MARL framework where agents communicate discretely without a central control unit. ClusterComm utilizes Mini-Batch-K-Means clustering on the last hidden layer’s activations of an agent’s policy network, translating them into discrete messages. This approach outperforms no communication and competes favorably with unbounded, continuous communication and hence poses a simple yet effective strategy for enhancing collaborative task-solving in MARL.

• Dokumententyp: Konferenzbeitrag (Paper)
• Fakultät: Mathematik, Informatik und Statistik > Informatik > Künstliche Intelligenz und Maschinelles Lernen
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• ISBN: 978-989-758-680-4
• Ort: Setúbal
• Sprache: Englisch