Generating Explanations for Temporal Logic Planner Decisions
Generating Explanations for Temporal Logic Planner Decisions
复制标题
DOI：
10.1609/icaps.v30i1.6740
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Daniel Kasenberg;Ravenna Thielstrom;matthias. scheutz
中科院分区：
文献类型：
--
作者：
Daniel Kasenberg;Ravenna Thielstrom;matthias. scheutz
尽管时态逻辑一直被吹捧为一种用于指定可解释智能体目标的富有成效的语言，但对于具有时态逻辑目标的智能体生成解释却鲜有强调。在本文中，我们开发了一种为具有多个时态逻辑目标进行规划的智能体的行为生成解释的方法。我们关注在确定性马尔可夫决策过程（MDPs）中运行的智能体，并使用线性时态逻辑（LTL）来指定目标。给定一个在确定性MDP中计划最大程度地满足一组LTL目标（具有相关偏好结构）的智能体，我们引入一种算法来构建回答事实性和“为什么”查询的解释，这些查询也用LTL指定。
Although temporal logic has been touted as a fruitful language for specifying interpretable agent objectives, there has been little emphasis on generating explanations for agents with temporal logic objectives. In this paper, we develop an approach to generating explanations for the behavior of agents planning with several temporal logic objectives. We focus on agents operating in deterministic Markov decision processes (MDPs), and specify objectives using linear temporal logic (LTL). Given an agent planning to maximally satisfy some set of LTL objectives (with an associated preference structure) in a deterministic MDP, we introduce an algorithm for constructing explanations answering both factual and “why” queries, which queries are also specified in LTL.