Abstract
Modern vision-based reinforcement learning techniques often use convolutional neural networks (CNN) as universal function approximators to choose which action to take for a given visual input. Until recently, CNNs have been treated like black-box functions, but this mindset is especially dangerous when used for control in safety-critical settings. In this paper, we present our extensions of CNN visualization algorithms to the domain of vision-based reinforcement learning. We use a simulated drone environment as an example scenario. These visualization algorithms are an important tool for behavior introspection and provide insight into the qualities and flaws of trained policies when interacting with the physical world. A video may be seen at this https URL
Abstract (translated)
现代基于视觉的强化学习技术通常使用卷积神经网络（CNN）作为通用函数逼近器来选择对给定视觉输入采取哪种动作。直到最近，CNN一直被视为黑盒功能，但这种思维方式在安全关键设置中用于控制时尤其危险。在本文中，我们将CNN可视化算法的扩展呈现给基于视觉的强化学习领域。我们使用模拟无人机环境作为示例场景。这些可视化算法是行为内省的重要工具，可以提供与物理世界交互时受过训练的策略的质量和缺陷的洞察力。可以在此https网址上看到视频
URL
https://arxiv.org/abs/1809.06781
