一句话：提出用松弛构造蜕变关系，为学习型动作策略测试提供 oracle，以区分策略缺陷与不可避免行为。
学习到的动作策略（如神经网络策略）若产生失败条件等不良或致命行为，测试可帮助建立信任；难点在于判断该行为是策略决策错误，还是在给定环境下不可避免，后者需要最优解知识，会破坏测试可扩展性，类似软件测试中不知道正确输出时的 oracle 问题。本文提出用松弛（relaxations）构造蜕变关系（metamorphic relations），从而在无需最优解的情况下为动作策略测试获得 oracle，以区分真正的策略缺陷与不可避免行为。给出的摘要未报告具体实验与结果。
Testing is a promising way to gain trust in a learned action policy π, in particular if π is a neural network. A “bug” in this context constitutes undesirable or fatal policy behavior, e.g., satisfying a failure condition. But how do we distinguish whether such behavior is due to bad policy decisions, or whether it is actually unavoidable under the given circumstances? This requires knowledge about optimal solutions, which defeats the scalability of testing. Related problems occur in software testing when the correct program output is not known.
@inproceedings{paperbot7415,
title = {Metamorphic relations via relaxations: an approach to obtain oracles for action-policy testing},
author = {Hasan Ferit Eniser and Timo P. Gros and Valentin Wüstholz and Jörg Hoffmann and Maria Christakis},
booktitle = {ISSTA},
year = {2022},
doi = {10.1145/3533767.3534392}
}