Risk-aware analysis for interpretations of probabilistic achievement and maintenance commitments

Risk-aware analysis for interpretations of probabilistic achievement and maintenance commitments
复制标题

用于解释概率成就和维护承诺的风险意识分析

DOI:
10.1016/j.artint.2023.103864
复制
发表时间:
2023
影响因子:
14.4
通讯作者:
Singh, Satinder
Singh, Satinder
中科院分区:
计算机科学2区
文献类型:
--
作者:
Zhang, Qi;Durfee, Edmund H.;Singh, Satinder

文献摘要

参考文献

相似文献

概率承诺为多代理协调提供了一个计算框架,其中一个自主代理(承诺提供者)承诺未来的行动过程,该行动过程以接受者希望的方式概率地影响另一个代理(承诺接受者)的本地状态。通常,概率承诺是抽象地指定的,以便在运行时给予提供者关于如何实现它的自由。不幸的是,正如我们在本文中分析的那样,这种抽象会给接收者带来性能欠佳的风险。对于提供者的(成就)承诺,以实现接受者喜欢但最初不成立的条件,我们证明了接受者可以做出约束其次优性风险的建模选择。然而,有些令人惊讶的是,对于提供者承诺维持初始值已经是接受者喜欢的条件的(维护),我们证明了不可能有这样的次优性风险界限。我们对这两种类型的承诺进行了实证研究,以衡量它们在不同条件下产生的次优性,并根据我们的理论和实证结果表明,在指定概率维持承诺时添加选择性细节是有益的。
Probabilistic commitments provide a computational framework for multi-agent coordination, where one autonomous agent (the commitment provider), commits to a future course of action that probabilistically influences the local state of another agent (the commitment recipient) in ways that the recipient desires. Conventionally, a probabilistic commitment is specified abstractly so as to give the provider latitude at run time about how to achieve it. Unfortunately, as we analyze in this article, this abstraction incurs a risk of suboptimal performance for the recipient. For (achievement) commitments by the provider to achieve conditions that the recipient prefers but that do not initially hold, we prove that the recipient can make modeling choices that bound its risk of suboptimality. Somewhat surprisingly, however, for (maintenance) commitments by the provider to maintain conditions whose initial values are already ones the recipient prefers, we prove that no such bounds on suboptimality risk are possible. We study the two types of commitments empirically to measure the suboptimality they incur under different conditions, and based on our theoretical and empirical results suggest that adding selective details when specifying probabilistic maintenance commitments can be beneficial.
承诺驱动的分布式联合政策搜索
DOI: 10.1145/1329125.1329216
发表时间: 2007
影响因子: 1.9
作者:
S. Witwicki;E. Durfee
通讯作者: E. Durfee
实现协作任务和团队维护
DOI: 10.1145/1329125.1329214
发表时间: 2007
期刊: ArXiv
影响因子: --
作者:
G. Kaminka;A. Yakir;Dan Erusalimchik;Nirom Cohen
通讯作者: Nirom Cohen
最小化承诺约束的顺序决策中的最大遗憾
DOI: 10.1609/icaps.v27i1.13836
发表时间: 2017
影响因子: 1.9
作者:
Qi Zhang;Satinder Singh;E. Durfee
通讯作者: E. Durfee
DOI: 10.1609/aaai.v35i13.17356
发表时间: 2020
期刊: ArXiv
影响因子: --
作者:
Qi Zhang;E. Durfee;Satinder Singh
通讯作者: Satinder Singh
在基于行为的机器人中实现灵活的团队合作:扩展摘要
DOI: 10.1145/1082473.1082770
发表时间: 2005
影响因子: 1.9
作者:
G. Kaminka;Inna Frenkel
通讯作者: Inna Frenkel