arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.06080cs.LG
收藏

TDM:通过可解释性增强实现可信决策

TDM: Trustworthy Decision-Making via Interpretability Enhancement

Auburn University(奥本大学);NVIDIA Corporation(英伟达公司);University at Buffalo(布法罗大学)

Daoming Lyu, Fangkai Yang, Hugh Kwon, Wen Dong, Levent Yilmaz, Bo Liu

摘要:

人机交互决策越来越普遍,信任是决定自主性依赖的一个影响因素。然而,信任超出我们理解范围的系统是不合理的,典型的机器学习和数据驱动决策是黑盒范例,阻碍了可解释性。因此,建立由可解释性感知策略增强的计算可信决策机制至关重要。为此,我们提出了一个可信的决策(TDM)框架,它集成了符号规划到顺序决策。该框架学习可解释的子任务,导致一个复杂的,更高层次的复合任务,可以正式评估使用建议的信任度量。TDM通过设计实现了子任务级的可解释性,并从学习的子任务收敛到最佳符号计划。此外,一个基于TDM的算法被引入到演示符号规划与其他顺序决策算法的统一,收获两者的好处。实验结果验证了基于信任分数的规划方法的有效性,同时提高了子任务的可解释性。

英文摘要:

Human-robot interactive decision-making is increasingly becoming ubiquitous, and trust is an influential factor in determining the reliance on autonomy. However, it is not reasonable to trust systems that are beyond our comprehension, and typical machine learning and data-driven decision-making are black-box paradigms that impede interpretability. Therefore, it is critical to establish computational trustworthy decision-making mechanisms enhanced by interpretability-aware strategies. To this end, we propose a Trustworthy Decision-Making (TDM) framework, which integrates symbolic planning into sequential decision-making. The framework learns interpretable subtasks that result in a complex, higher-level composite task that can be formally evaluated using the proposed trust metric. TDM enables the subtask-level interpretability by design and converges to an optimal symbolic plan from the learned subtasks. Moreover, a TDM-based algorithm is introduced to demonstrate the unification of symbolic planning with other sequential-decision making algorithms, reaping the benefits of both. Experimental results validate the effectiveness of trust-score-based planning while improving the interpretability of subtasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑