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 1701.08317cs.AI
收藏

作为模型和解的计划解释:超越作为独白的解释

Plan Explanations as Model Reconciliation: Moving Beyond Explanation as Soliloquy

Arizona State University(亚利桑那州立大学)

Tathagata Chakraborti, Sarath Sreedharan, Yu Zhang, Subbarao Kambhampati

摘要:

当人工智能系统在循环中与人类互动时,它们经常被要求为自己的计划和行为提供解释。过去关于计划解释的工作主要涉及人工智能系统解释其计划的正确性以及根据自己的模型做出决定的理由。这种独白在大多数现实场景中是完全不够的,在这些场景中,人类的领域和任务模型与人工智能系统所使用的模型有很大的不同。我们认为,最好根据这些不同的模型来研究这些解释。特别是,我们展示了解释如何被视为一个“模型协调问题”(MRP),其中人工智能系统实际上建议改变人类的模型,以便使其计划相对于改变后的人类模型是最优的。我们将研究这些解释的性质,提出自动计算它们的算法,并评估算法的性能。

英文摘要:

When AI systems interact with humans in the loop, they are often called on to provide explanations for their plans and behavior. Past work on plan explanations primarily involved the AI system explaining the correctness of its plan and the rationale for its decision in terms of its own model. Such soliloquy is wholly inadequate in most realistic scenarios where the humans have domain and task models that differ significantly from that used by the AI system. We posit that the explanations are best studied in light of these differing models. In particular, we show how explanation can be seen as a "model reconciliation problem" (MRP), where the AI system in effect suggests changes to the human's model, so as to make its plan be optimal with respect to that changed human model. We will study the properties of such explanations, present algorithms for automatically computing them, and evaluate the performance of the algorithms.

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。

↑