用世界模型模拟未来计划，比让智能体自己学沟通更高效。
Communicating Plans, Not Percepts: Scalable Multi-Agent Coordination with Embodied World Models
- 用自研世界模型预测未来状态，生成压缩后的行动计划消息
- 在复杂网格环境中，性能、效率和可扩展性均优于自学习沟通
- 适合需要高效协作的多智能体系统，如机器人团队调度
在部分可观测环境下，多智能体系统中的稳健协调对决策至关重要。本文探讨了多智能体强化学习（MARL）中通信协议应人为设计还是端到端学习的问题。研究采用具身世界模型，提出两种协作任务分配策略：第一种为端到端学习的直接通信（LDC）；第二种为基于工程归纳偏置的意图通信，利用一个紧凑的、可学习的世界模型——想象轨迹生成模块（ITGM），结合智能体自身策略模拟未来状态，再通过消息生成网络（MGN）将计划压缩为消息。在网格世界这一典型具身智能抽象场景中，随着环境复杂度增加，实验表明尽管涌现通信在简单情况下可行，但基于世界模型的工程化方法在性能、样本效率和可扩展性上均表现更优。结果支持在MARL中引入结构化预测模型，以实现主动、目标驱动的协作。
原文摘要 · Abstract (English)
Robust coordination is critical for effective decision-making in multi-agent systems, especially under partial observability. A central question in Multi-Agent Reinforcement Learning (MARL) is whether to engineer communication protocols or learn them end-to-end. We investigate this dichotomy using embodied world models. We propose and compare two communication strategies for a cooperative task-allocation problem. The first, Learned Direct Communication (LDC), learns a protocol end-to-end. The second, Intention Communication, uses an engineered inductive bias: a compact, learned world model, the Imagined Trajectory Generation Module (ITGM), which uses the agent's own policy to simulate future states. A Message Generation Network (MGN) then compresses this plan into a message. We evaluate these approaches on goal-directed interaction in a grid world, a canonical abstraction for embodied AI problems, while scaling environmental complexity. Our experiments reveal that while emergent communication is viable in simple settings, the engineered, world model-based approach shows superior performance, sample efficiency, and scalability as complexity increases. These findings advocate for integrating structured, predictive models into MARL agents to enable active, goal-driven coordination.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。