Asking the Right Questions: Learning Interpretable Action Models Through Query Answering
Asking the Right Questions: Learning Interpretable Action Models Through Query Answering
复制标题
DOI：
10.1609/aaai.v35i13.17428
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Pulkit Verma;Shashank Rao Marpally;Siddharth Srivastava
中科院分区：
文献类型：
--
作者：
Pulkit Verma;Shashank Rao Marpally;Siddharth Srivastava
本文开发了一种新方法来估计可以计划和行动的黑盒自主代理的可解释的关系模型。我们的主要贡献是使用代理的基本查询接口和分层查询算法来估计此类模型的新范例，该算法生成询问策略以在用户可解释的词汇中估计代理的内部模型。对我们方法的实证评估表明，尽管可能的代理模型的搜索空间很棘手，但我们的方法允许对各种黑盒自主代理的可解释代理模型进行正确且可扩展的估计。我们的结果还表明，这种方法可以使用谓词分类器来学习将状态表示为图像的规划代理的可解释模型。
This paper develops a new approach for estimating an interpretable, relational model of a black-box autonomous agent that can plan and act. Our main contributions are a new paradigm for estimating such models using a rudimentary query interface with the agent and a hierarchical querying algorithm that generates an interrogation policy for estimating the agent's internal model in a user-interpretable vocabulary. Empirical evaluation of our approach shows that despite the intractable search space of possible agent models, our approach allows correct and scalable estimation of interpretable agent models for a wide class of black-box autonomous agents. Our results also show that this approach can use predicate classifiers to learn interpretable models of planning agents that represent states as images.