论文标题
导航代理商对他们的环境有什么了解？
What do navigation agents learn about their environment?
论文作者
论文摘要
当今的最先进的视觉导航代理通常由大型深度学习模型端到端组成。这样的模型几乎没有关于学习的技能或代理商对环境所采取的行动的解释性。尽管过去的作品探索了解释深度学习模型，但很少关注解释体现的AI系统，这通常涉及对环境结构，目标特征和行动的结果进行推理。在本文中，我们介绍了用于点目标和对象目标导航代理的体现代理（ISEE）的可解释性系统。我们使用ISEE来探测这些代理产生的动态表示，以了解有关代理和环境的信息。我们展示了使用ISEE的有关导航剂的有趣见解，包括能够编码可及地点的能力（避免障碍物），目标的可见性，最初产卵位置的进展以及当我们掩盖关键个体神经元时对代理行为的巨大影响。该代码可在以下网址找到：https：//github.com/allenai/isee
Today's state of the art visual navigation agents typically consist of large deep learning models trained end to end. Such models offer little to no interpretability about the learned skills or the actions of the agent taken in response to its environment. While past works have explored interpreting deep learning models, little attention has been devoted to interpreting embodied AI systems, which often involve reasoning about the structure of the environment, target characteristics and the outcome of one's actions. In this paper, we introduce the Interpretability System for Embodied agEnts (iSEE) for Point Goal and Object Goal navigation agents. We use iSEE to probe the dynamic representations produced by these agents for the presence of information about the agent as well as the environment. We demonstrate interesting insights about navigation agents using iSEE, including the ability to encode reachable locations (to avoid obstacles), visibility of the target, progress from the initial spawn location as well as the dramatic effect on the behaviors of agents when we mask out critical individual neurons. The code is available at: https://github.com/allenai/iSEE
