Comparing The Accuracy of Frequentist and Bayesian Models in Human-Agent Negotiation

Comparing The Accuracy of Frequentist and Bayesian Models in Human-Agent Negotiation
复制标题

比较人类代理协商中频率论模型和贝叶斯模型的准确性

DOI:
10.1145/3472306.3478354
复制
发表时间:
2021
期刊:
Proceedings of the 21st ACM International Conference on Intelligent Virtual Agents
影响因子:
--
通讯作者:
Gratch, Jonathan
Gratch, Jonathan
中科院分区:
--
文献类型:
--
作者:
Johnson, Emmanuel;Gratch, Jonathan

文献摘要

参考文献

被引文献

相似文献

了解对手的需求对于最大化多问题谈判的结果至关重要。为此,自动化系统必须根据谈判期间传达的信息构建“对手模型”。贝叶斯模型和频率模型是最常用的。贝叶斯模型有一种原则性的方法来整合有关对手偏好的先验知识。然而,频率论模型在实践中胜过贝叶斯方法,在年度代理与代理谈判竞赛中占据主导地位。随着人们对与人谈判的代理人越来越感兴趣,这种假定的主导地位需要重新审视。人类对手传达的信息比自动化代理少得多,而且人们通常有相似的偏好(例如,在薪资谈判中,大多数人最关心薪资)。因此,贝叶斯方法的理论优势可以转化为代理与人类谈判的实践。在这项工作中,我们在代理与人类的多问题薪资谈判中将贝叶斯模型的性能与领先的频率论方法进行比较。尽管我们表明,在使用统一先验时,频率论对手模型优于贝叶斯模型,但在使用两个共同先验时,贝叶斯方法表现出色。最佳性能是通过经验得出的先验来实现的(即,使用过去人类谈判者中发现的偏好分布来偏置模型空间)。然而,当使用“固定馅饼偏差”(大多数人类谈判者使用的先验)时,也观察到了强劲的表现。我们讨论这些发现对人类代理谈判研究的影响。
Understanding an opponent's wants is crucial for maximizing the outcomes of a multi-issue negotiation. To do this, automated systems must build an "opponent model" from information conveyed during a negotiation. Bayesian and frequentist models are the most commonly used. Bayesian models have a principled way to incorporate prior knowledge about an opponent's preferences. However, frequentist models have outperformed Bayesian approaches in practice, dominating the yearly agent-verses-agent negotiation competitions. With growing interest in agents that negotiate with people, this presumed dominance needs to be revisited. Human opponents convey far less information than automated agents, and people often share similar preferences (e.g., in a salary negotiation, most people care the most about salary). Thus, the theoretical advantage of Bayesian approaches may translate into practice for agent-versus-human negotiation. In this work, we compare the performance of Bayesian models against a leading frequentist approach in an agent-versus-human multi-issue salary negotiation. Although we show that frequentist opponent models outperform Bayesian models when using a uniform prior, Bayesian approaches excel when using two common priors. The best performance is achieved with an empirically-derived prior (i.e., biasing the model space using the distribution of preferences found in past human negotiators). Yet, strong performance is also observed when using a "fixed-pie bias", the prior used by most human negotiators. We discuss the implication of these findings for research on human-agent negotiation.
DOI: 10.1007/978-3-642-24696-8_7
发表时间: 2012
期刊: --
影响因子: --
作者:
T. Baarslag;K. Hindriks;C. Jonker;Sarit Kraus;R. Lin
通讯作者: T. Baarslag;K. Hindriks;C. Jonker;Sarit Kraus;R. Lin
复杂的自动化谈判:理论、模型和软件竞赛
DOI: --
发表时间: 2012
期刊: Complex Automated Negotiations
影响因子: --
作者:
Takayuki Ito;Minjie Zhang;V. Robu;T. Matsuo
通讯作者: T. Matsuo
通过有效的通用对手建模应对人类与代理谈判的挑战
DOI: --
发表时间: 2009
期刊: Adaptive Agents and Multi-Agent Systems
影响因子: --
作者:
Yinon Oshrat;R. Lin;Sarit Kraus
通讯作者: Sarit Kraus
DOI: --
发表时间: 1990
期刊: Psychology Review
影响因子: --
作者:
Dominic W. Massaro;Daniel Friedman
通讯作者: Daniel Friedman
虚拟人类谈判者的对手建模
DOI: 10.1007/978-3-319-21996-7_4
发表时间: 2015
影响因子: 3
作者:
Zahra Nazari;Gale M. Lucas;J. Gratch
通讯作者: J. Gratch