學習合作: 多智能體導航中的緊急通信（CS LG）

• 2020 年 4 月 6 日
• 筆記

人工智能中的緊急通信已經被用來研究語言進化，以及開發學習與人類交流的人工系統。我們展示了在不同的網格世界環境中代理執行協同導航任務來了解一個可解釋的通信協議，使他們能夠有效、最佳地在許多情況下解決任務。對代理策略的分析表明，緊急信號在空間上聚集了狀態空間，信號指向特定的位置和空間方向，如「左」、「上」或「左上房間」。 利用代理群體，我們證明了緊急協議具有基本的組合結構，從而展現了自然語言的核心特性。

Learning to cooperate: Emergent communication in multi-agent navigation

Emergent communication in artificial agents has been studied to understand language evolution, as well as to develop artificial systems that learn to communicate with humans. We show that agents performing a cooperative navigation task in various gridworld environments learn an interpretable communication protocol that enables them to efficiently, and in many cases, optimally, solve the task. An analysis of the agents' policies reveals that emergent signals spatially cluster the state space, with signals referring to specific locations and spatial directions such as "left", "up", or "upper left room". Using populations of agents, we show that the emergent protocol has basic compositional structure, thus exhibiting a core property of natural language.

原文作者：Ivana Kajić

原文地址：https://arxiv.org/abs/2004.01097