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 2203.08895cs.AI
收藏

解释偏好驱动的时间表:EXPRES框架

Explaining Preference-driven Schedules: the EXPRES Framework

J.P. Morgan AI Research(摩根大通人工智能研究院);Bar-Ilan University(巴伊兰大学)

Alberto Pozanco, Francesca Mosca, Parisa Zehtabi, Daniele Magazzeni, Sarit Kraus

摘要:

调度是将一组随时间分布的稀缺资源分配给一组代理的任务,这些代理通常对他们想要获得的分配有偏好。由于这些问题的约束性质,满足所有代理人的偏好往往是不可行的,这可能会导致一些代理人不满意所得到的时间表。提供解释已被证明可以提高对人工智能工具产生的解决方案的满意度和信任度。然而,解释受多个代理人影响和影响的解决方案特别具有挑战性。在本文中,我们介绍了EXPRESS框架,它可以解释为什么一个给定的偏好是不满足在一个给定的最优调度。EXPRESS框架包括:(i)一个解释生成器,基于混合线性规划模型,找到可以解释不满意偏好的最佳原因集;以及(ii)一个解释解析器,将生成的解释转换为人类可解释的解释。通过模拟,我们表明,解释生成器可以有效地扩展到大型实例。最后,通过一组用户在摩根大通的研究,我们表明,员工更喜欢的解释时,考虑劳动力调度方案的表达产生的人产生的。

英文摘要:

Scheduling is the task of assigning a set of scarce resources distributed over time to a set of agents, who typically have preferences about the assignments they would like to get. Due to the constrained nature of these problems, satisfying all agents' preferences is often infeasible, which might lead to some agents not being happy with the resulting schedule. Providing explanations has been shown to increase satisfaction and trust in solutions produced by AI tools. However, it is particularly challenging to explain solutions that are influenced by and impact on multiple agents. In this paper we introduce the EXPRES framework, which can explain why a given preference was unsatisfied in a given optimal schedule. The EXPRES framework consists of: (i) an explanation generator that, based on a Mixed-Integer Linear Programming model, finds the best set of reasons that can explain an unsatisfied preference; and (ii) an explanation parser, which translates the generated explanations into human interpretable ones. Through simulations, we show that the explanation generator can efficiently scale to large instances. Finally, through a set of user studies within J.P. Morgan, we show that employees preferred the explanations generated by EXPRES over human-generated ones when considering workforce scheduling scenarios.

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。

↑