让智能体通过隐性动作通道高效传递信息，提升协作效率。
Learning to Communicate Through Implicit Communication Channels
- 用特定探测动作作为信息载体，建立编码解码映射实现隐性通信。
- 在猜数字、揭示目标和Hanabi游戏中性能显著优于基线方法。
- 适用于无显式消息机制的复杂协作场景，适合多智能体系统研究者。
有效沟通是协作型多智能体系统的关键。历史上人类社会常面临无法使用显式通信的情形，这推动了隐性通信的研究。以往基于心理理论（ToM）的方法依赖智能体通过观察行为推断他人意图，但在复杂任务中推断精度下降。本文提出隐性通道协议（ICP）框架，使智能体可通过类似显式通信的隐性通道交流。ICP利用一组特定动作（称为探测动作），并建立信息与这些动作之间的映射以实现消息的编码与解码。我们设计了两种训练算法：基于随机初始化信息映射和延迟更新信息映射。ICP在猜数字、揭示目标和Hanabi任务中均显著优于基线方法，实现了更高效的隐性信息传递。
原文摘要 · Abstract (English)
Effective communication is an essential component in collaborative multi-agent systems. Situations where explicit messaging is not feasible have been common in human society throughout history, which motivate the study of implicit communication. Previous works on learning implicit communication mostly rely on theory of mind (ToM), where agents infer the mental states and intentions of others by interpreting their actions. However, ToM-based methods become less effective in making accurate inferences in complex tasks. In this work, we propose the Implicit Channel Protocol (ICP) framework, which allows agents to communicate through implicit communication channels similar to the explicit ones. ICP leverages a subset of actions, denoted as the scouting actions, and a mapping between information and these scouting actions that encodes and decodes the messages. We propose training algorithms for agents to message and act, including learning with a randomly initialized information map and with a delayed information map. The efficacy of ICP has been tested on the tasks of Guessing Numbers, Revealing Goals, and Hanabi, where ICP significantly outperforms baseline methods through more efficient information transmission.
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。