CoDreamer: Communication-Based Decentralised World Models

2024/06/19 by Edan Toledo, Amanda Prorok, Toledo, Edan +1 · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Mobile Agent-Based Network Management

paper · pdf · doi:10.48550/arxiv.2406.13600

openalex publication_date 2024/06/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Sample efficiency is a critical challenge in reinforcement learning. Model-based RL has emerged as a solution, but its application has largely been confined to single-agent scenarios. In this work, we introduce CoDreamer, an extension of the Dreamer algorithm for multi-agent environments. CoDreamer leverages Graph Neural Networks for a two-level communication system to tackle challenges such as partial observability and inter-agent cooperation. Communication is separately utilised within the learned world models and within the learned policies of each agent to enhance modelling and task-solving. We show that CoDreamer offers greater expressive power than a naive application of Dreamer, and we demonstrate its superiority over baseline methods across various multi-agent environments.

Cited by

• Empowering Multi-Robot Cooperation via Sequential World Models
• In-Context Reinforcement Learning via Communicative World Models

Related

• Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learning
• MA-Dreamer: Coordination and communication through shared imagination
• HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging
• Communicating Plans, Not Percepts: Scalable Multi-Agent Coordination with Embodied World Models
• Scalable Multi-Agent Model-Based Reinforcement Learning