M2I2: Learning Efficient Multi-Agent Communication via Masked State Modeling and Intention Inference

2024-12-31

AI Summary

To address low coordination efficiency in multi-robot systems caused by insufficient information integration, this paper proposes a masked state-intent joint modeling framework. It implicitly models occluded environmental states and teammates’ latent intentions to enhance agents’ understanding of and responsiveness to uncertain interactions. Furthermore, we design a dimension-rational network (DRN) based on meta-learning to assess the importance of communication dimensions and enable interpretable, selective information sharing. The method integrates masked state modeling, joint action prediction, and an importance-driven heuristic information masking mechanism. Evaluated across diverse complex multi-agent tasks, our approach significantly outperforms state-of-the-art methods: it reduces communication overhead by 23%–37%, improves decision quality by 18%–29%, and demonstrates strong cross-scenario generalization capability.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Multiagent Systems: Agent Communication
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Communication is essential in coordinating the behaviors of multiple agents. However, existing methods primarily emphasize content, timing, and partners for information sharing, often neglecting the critical aspect of integrating shared information. This gap can significantly impact agents' ability to understand and respond to complex, uncertain interactions, thus affecting overall communication efficiency. To address this issue, we introduce M2I2, a novel framework designed to enhance the agents' capabilities to assimilate and utilize received information effectively. M2I2 equips agents with advanced capabilities for masked state modeling and joint-action prediction, enriching their perception of environmental uncertainties and facilitating the anticipation of teammates' intentions. This approach ensures that agents are furnished with both comprehensive and relevant information, bolstering more informed and synergistic behaviors. Moreover, we propose a Dimensional Rational Network, innovatively trained via a meta-learning paradigm, to identify the importance of dimensional pieces of information, evaluating their contributions to decision-making and auxiliary tasks. Then, we implement an importance-based heuristic for selective information masking and sharing. This strategy optimizes the efficiency of masked state modeling and the rationale behind information sharing. We evaluate M2I2 across diverse multi-agent tasks, the results demonstrate its superior performance, efficiency, and generalization capabilities, over existing state-of-the-art methods in various complex scenarios.

Problem

• Multi-robot collaboration
• Information integration
• Efficiency in complex environments

Innovation

• Multi-Robot Collaboration
• Uncertainty Prediction
• Advanced Communication Strategies