arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.09780cs.AI
收藏

基于归因的马尔可夫决策过程解释

Attribution-based Explanations for Markov Decision Processes

University of Oslo(奥斯陆大学);Imperial College London(伦敦帝国理工学院);RWTH Aachen University(亚琛工业大学)

Paul Kobialka, Andrea Pferscher, Francesco Leofante, Erika Ábrahám, Silvia Lizeth Tapia Tarifa, Einar Broch Johnsen

AI总结:

本文提出基于归因的马尔可夫决策过程解释方法,通过策略合成技术计算状态和执行路径的重要性分数,提升序列决策代理的可解释性。

摘要:

归因技术通过给AI模型的输入分配数值分数来解释其输出。迄今为止,这些技术主要集中在单时间点静态输入特征的重要性归因上,无法推广到序列决策设置。本文填补了这一空白,引入生成马尔可夫决策过程(MDP)归因解释的技术。我们给出了MDP中归因应代表什么的正式表征,重点在于为个体状态和执行路径分配重要性分数。我们展示了如何利用策略合成技术计算重要性分数,尽管MDP固有的非确定性,仍能高效计算这些分数。我们在五个案例研究中评估了我们的方法,证明了其在提供序列决策代理逻辑可解释性方面的有效性。

英文摘要:

Attribution techniques explain the outcome of an AI model by assigning a numerical score to its inputs. So far, these techniques have mainly focused on attributing importance to static input features at a single point in time, and thus fail to generalize to sequential decision-making settings. This paper fills this gap by introducing techniques to generate attribution-based explanations for Markov Decision Processes (MDPs). We give a formal characterization of what attributions should represent in MDPs, focusing on explanations that assign importance scores to both individual states and execution paths. We show how importance scores can be computed by leveraging techniques for strategy synthesis, enabling the efficient computation of these scores despite the non-determinism inherent in an MDP. We evaluate our approach on five case-studies, demonstrating its utility in providing interpretable insights into the logic of sequential decision-making agents.

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。

↑