文章基本信息

标题：Explainable AI methods on a deep reinforcement learning agent for automatic docking ⁎
本地全文：下载
作者：Jakob Løver ; Vilde B. Gjærum ; Anastasios M. Lekkas 等
期刊名称：IFAC PapersOnLine
印刷版ISSN：2405-8963
出版年度：2021
卷号：54
期号：16
页码：146-152
DOI：10.1016/j.ifacol.2021.10.086
语种：English
出版社：Elsevier
摘要：AbstractArtifical neural networks (ANNs) have made their way into marine robotics in the last years, where they are used in control and perception systems, to name a few examples. At the same time, the black-box nature of ANNs is responsible for key challenges related to interpretability and trustworthiness, which need to be addressed if ANNs are to be deployed safely in real-life operations. In this paper, we implement three XAI methods to provide explanations to the decisions made by a deep reinforcement learning agent: Kernel SHAP, LIME and Linear Model Trees (LMTs). The agent was trained via Proximal Policy Optimization (PPO) to perform automatic docking on a fully-actuated vessel. We discuss the properties and suitability of the three methods, and juxtapose them with important attributes of the docking agent to provide context to the explanations.
关键词：KeywordsMarine control systemsExplainable Artificial IntelligenceDeep Reinforcement LearningAutonomous shipsDocking