Decentralized Collective World Model for Emergent Communication and Coordination
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915928141201408 |
|---|---|
| author | Nomura, Kentaro Aoki, Tatsuya Taniguchi, Tadahiro Horii, Takato |
| author_facet | Nomura, Kentaro Aoki, Tatsuya Taniguchi, Tadahiro Horii, Takato |
| contents | We propose a fully decentralized multi-agent world model that enables both symbol emergence for communication and coordinated behavior through temporal extension of collective predictive coding. Unlike previous research that focuses on either communication or coordination separately, our approach achieves both simultaneously. Our method integrates world models with communication channels, enabling agents to predict environmental dynamics, estimate states from partial observations, and share critical information through bidirectional message exchange with contrastive learning for message alignment. Using a two-agent trajectory drawing task, we demonstrate that our communication-based approach outperforms non-communicative models when agents have divergent perceptual capabilities, achieving the second-best coordination after centralized models. Importantly, our decentralized approach with constraints preventing direct access to other agents' internal states facilitates the emergence of more meaningful symbol systems that accurately reflect environmental states. These findings demonstrate the effectiveness of decentralized communication for supporting coordination while developing shared representations of the environment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03353 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Decentralized Collective World Model for Emergent Communication and Coordination Nomura, Kentaro Aoki, Tatsuya Taniguchi, Tadahiro Horii, Takato Multiagent Systems Artificial Intelligence We propose a fully decentralized multi-agent world model that enables both symbol emergence for communication and coordinated behavior through temporal extension of collective predictive coding. Unlike previous research that focuses on either communication or coordination separately, our approach achieves both simultaneously. Our method integrates world models with communication channels, enabling agents to predict environmental dynamics, estimate states from partial observations, and share critical information through bidirectional message exchange with contrastive learning for message alignment. Using a two-agent trajectory drawing task, we demonstrate that our communication-based approach outperforms non-communicative models when agents have divergent perceptual capabilities, achieving the second-best coordination after centralized models. Importantly, our decentralized approach with constraints preventing direct access to other agents' internal states facilitates the emergence of more meaningful symbol systems that accurately reflect environmental states. These findings demonstrate the effectiveness of decentralized communication for supporting coordination while developing shared representations of the environment. |
| title | Decentralized Collective World Model for Emergent Communication and Coordination |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2504.03353 |