ClusterComm: Discrete Communication in Decentralized MARL using Internal Representation Clustering

2024/01/07 by Robert Müller, Müller, Robert, Hasan Turalic +9 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.2401.03504

openalex publication_date 2024/01/07 · openalex created_date 2024/01/13 · openalex updated_date 2026/07/28

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.

Cited by

• LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learning

Related

• Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning
• HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging
• Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel
• Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?
• Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances