Improving Fairness in Adaptive Social Exergames via Shapley Bandits

Improving Fairness in Adaptive Social Exergames via Shapley Bandits
复制标题

通过 Shapley Bandits 提高自适应社交运动游戏的公平性

DOI:
10.1145/3581641.3584050
复制
发表时间:
2023
期刊:
Proceedings of the 28th International Conference on Intelligent User Interfaces
影响因子:
--
通讯作者:
Zhu, Jichen
Zhu, Jichen
中科院分区:
--
文献类型:
--
作者:
Gray, Robert C.;Villareale, Jennifer;Fox, Thomas Boyd;Dallal, Diane H.;Ontanon, Santiago;Arigo, Danielle;Jabbari, Shahin;Zhu, Jichen

文献摘要

参考文献

被引文献

相似文献

随着人工智能融入社会,算法公平性是一个基本要求。在人工智能分配资源的社交应用中,算法往往必须做出有利于一部分用户的决定,有时是重复或排他性的,同时试图最大化特定的结果。我们应该如何设计这样的系统,以便更公平地为用户服务?本文探讨了这样一个问题,即一群用户在一款名为Step Heroes的社交游戏中朝着一个共同的目标努力。我们确定了传统的多武装匪徒(MAB)的不良后果,并形式化了贪婪的匪徒问题。然后,我们提出了一种基于新型公平意识的多臂强盗Shapley Bandits的解决方案。它使用Shapley值来增加整体球员的参与度和干预依从性,而不是传统上通过偏爱表现优异的参与者来实现的总产出的最大化。我们通过一项用户研究(n=46)来评估我们的方法。我们的结果表明,Shapley Bandits有效地调解了贪婪的强盗问题,并在参与者之间实现了更好的用户保持和动机。
Algorithmic fairness is an essential requirement as AI becomes integrated in society. In the case of social applications where AI distributes resources, algorithms often must make decisions that will benefit a subset of users, sometimes repeatedly or exclusively, while attempting to maximize specific outcomes. How should we design such systems to serve users more fairly? This paper explores this question in the case where a group of users works toward a shared goal in a social exergame called Step Heroes. We identify adverse outcomes in traditional multi-armed bandits (MABs) and formalize the Greedy Bandit Problem. We then propose a solution based on a new type of fairness-aware multi-armed bandit, Shapley Bandits. It uses the Shapley Value for increasing overall player participation and intervention adherence rather than the maximization of total group output, which is traditionally achieved by favoring only high-performing participants. We evaluate our approach via a user study (n=46). Our results indicate that our Shapley Bandits effectively mediates the Greedy Bandit Problem and achieves better user retention and motivation across the participants.
多人游戏中的体验管理
DOI: --
发表时间: 2019
期刊: Proceedings of the 2019 IEEE Conference on Games
影响因子: --
作者:
Zhu, Jichen;Ontañón, Santiago
通讯作者: Ontañón, Santiago
使用人工智能方法对基于约束的调度系统进行调查
DOI: 10.1016/0954-1810(91)90001-5
发表时间: 1991
期刊: Artif. Intell. Eng.
影响因子: --
作者:
H. Atabakhsh
通讯作者: H. Atabakhsh
以玩家为中心的人工智能,用于自动游戏个性化:开放问题
DOI: 10.1145/3402942.3402951
发表时间: 2020
期刊: Proceedings of the Fifteenth International Conference on the Foundations of Digital Games (FDG ’20
影响因子: --
作者:
Zhu, Jichen;Ontañón, Santiago
通讯作者: Ontañón, Santiago
公寓电梯成本分摊规则的法律和经济学视角
DOI: --
发表时间: 2019
影响因子: 0.3
作者:
B. Crettez;Régis Deloche
通讯作者: Régis Deloche
Shapley值在货币公平除法中的应用
DOI: 10.2307/2951524
发表时间: 1992
期刊: Econometrica
影响因子: 6.1
作者:
H. Moulin
通讯作者: H. Moulin