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 2211.00478cs.AIcs.CV
收藏

通过意向立场理解不可预见

Understanding the Unforeseen via the Intentional Stance

UCLA(加州大学洛杉矶分校);GE Research(通用电气研究中心)

Stephanie Stacy, Alfredo Gabaldon, John Karigiannis, James Kubrich, Peter Tu

摘要:

我们提出了一个体系结构和系统,用于理解观察到的代理的新行为。我们的方法的两个主要特点是通过丹尼特的意向立场和类比推理的主要计算机制之一,理解不可预见的经验。我们的方法使用类比与过去的经验来构建假设的理由,解释观察到的代理人的行为。此外,我们认为类比是局部的;因此,多个过去的经验可以混合起来,以类比的方式解释一个不可预见的事件,从而导致更大的推理灵活性。我们认为,这种方法比基于表面水平比较的方法更有意义的解释所观察到的行为。行为解释相对于分类的一个关键优势是能够i)基于推理采取适当的响应,以及ii)做出允许验证假设解释的非平凡预测。我们提供了一个简单的用例,通过在加油站环境中进行类比来演示对新体验的理解。

英文摘要:

We present an architecture and system for understanding novel behaviors of an observed agent. The two main features of our approach are the adoption of Dennett's intentional stance and analogical reasoning as one of the main computational mechanisms for understanding unforeseen experiences. Our approach uses analogy with past experiences to construct hypothetical rationales that explain the behavior of an observed agent. Moreover, we view analogies as partial; thus multiple past experiences can be blended to analogically explain an unforeseen event, leading to greater inferential flexibility. We argue that this approach results in more meaningful explanations of observed behavior than approaches based on surface-level comparisons. A key advantage of behavior explanation over classification is the ability to i) take appropriate responses based on reasoning and ii) make non-trivial predictions that allow for the verification of the hypothesized explanation. We provide a simple use case to demonstrate novel experience understanding through analogy in a gas station environment.

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。

↑