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

TL;DR

M2I2 introduces a novel multi-agent communication framework that enhances information assimilation and utilization through masked state modeling, intention inference, and importance-based information sharing, leading to improved coordination and efficiency.

Contribution

The paper presents M2I2, a new framework combining masked state modeling, intention inference, and a Dimensional Rational Network trained via meta-learning for efficient multi-agent communication.

Findings

Outperforms existing methods in diverse multi-agent tasks.

Demonstrates improved communication efficiency and generalization.

Enhances agents' understanding of environmental uncertainties.

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.