arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.01532cs.AI
收藏

不确定性下自主智能体意图行为的分析

Analyzing Intentional Behavior in Autonomous Agents under Uncertainty

Graz University of Technology(格拉茨技术大学);Yale University(耶鲁大学);New York University(纽约大学)

Filip Cano Córdoba, Samuel Judson, Timos Antonopoulos, Katrine Bjørner, Nicholas Shoemaker, Scott J. Shapiro, Ruzica Piskac, Bettina Könighofer

AI总结:

本文提出在MDP框架下通过能动范围和反事实推理量化自主智能体意图行为证据,以区分有意与意外结果。

摘要:

在不确定环境中实现自主决策的原则性问责,需要区分有意造成的结果、因设计疏忽导致的结果和真正的事故。我们提出通过一种对意图行为证据的量化度量来分析自主智能体的行为。我们将不确定环境建模为马尔可夫决策过程(MDP)。对于给定场景,我们依靠概率模型检验来计算智能体影响到达某一特定事件的能力,并将其称为能动范围(scope of agency)。我们认为,如果能动范围较高,且智能体的决策接近到达该事件的最优决策,则存在意图行为的证据。我们的方法应用反事实推理来自动生成相关场景,通过分析这些场景来提高评估的可信度。在一个案例研究中,我们展示了该方法如何区分“有意”和“意外”的交通碰撞。

英文摘要:

Principled accountability for autonomous decision-making in uncertain environments requires distinguishing intentional outcomes from negligent designs from actual accidents. We propose analyzing the behavior of autonomous agents through a quantitative measure of the evidence of intentional behavior. We model an uncertain environment as a Markov Decision Process (MDP). For a given scenario, we rely on probabilistic model checking to compute the ability of the agent to influence reaching a certain event. We call this the scope of agency. We say that there is evidence of intentional behavior if the scope of agency is high and the decisions of the agent are close to being optimal for reaching the event. Our method applies counterfactual reasoning to automatically generate relevant scenarios that can be analyzed to increase the confidence of our assessment. In a case study, we show how our method can distinguish between 'intentional' and 'accidental' traffic collisions.

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。

↑