Using Cognitive Agents to Train Negotiation Skills.
Using Cognitive Agents to Train Negotiation Skills.
复制标题
DOI：
10.3389/fpsyg.2018.00154
复制
发表时间：
2018
影响因子：
3.8
通讯作者：
Taatgen NA
中科院分区：
文献类型：
--
作者：
Stevens CA;Daamen J;Gaudrain E;Renkema T;Top JD;Cnossen F;Taatgen NA
培训谈判是困难的，因为它是一个复杂的、动态的活动，涉及多方。通常不清楚如何创造学生练习谈判的环境，或者如何衡量学生的进步。一些学校已经开始通过创建人工软件代理来解决这些问题，学生可以用这些代理进行培训。这些代理的优势在于它们可以被“重置”，并且可以多次对抗。这可以让学生从错误中学习，并尝试不同的策略。然而，这些行为通常是基于谈判者应该如何行为的规范理论，而不一定是人们在谈判中的实际行为。在这里，我们通过开发基于认知架构的代理ACT-R来解决这一差距。这个智能体包含一个心智理论模型，即人类推断他人心理状态的能力。它使用这个模型来推断对手的策略并做出相应的反应。在一系列的实验中，我们证明了这种代理复制了人类表现的某些方面，对人类谈判者来说是合理的，并且可以在小规模的谈判任务中获得学习收益。
Training negotiation is difficult because it is a complex, dynamic activity that involves multiple parties. It is often not clear how to create situations in which students can practice negotiation or how to measure students' progress. Some have begun to address these issues by creating artificial software agents with which students can train. These agents have the advantage that they can be “reset,” and played against multiple times. This allows students to learn from their mistakes and try different strategies. However, these agents are often based on normative theories of how negotiators should conduct themselves, not necessarily how people actually behave in negotiations. Here, we take a step toward addressing this gap by developing an agent grounded in a cognitive architecture, ACT-R. This agent contains a model of theory-of-mind, the ability of humans to reason about the mental states of others. It uses this model to try to infer the strategy of the opponent and respond accordingly. In a series of experiments, we show that this agent replicates some aspects of human performance, is plausible to human negotiators, and can lead to learning gains in a small-scale negotiation task.
登录
查看更多内容
影响因子：
7.5
作者：
Cao, Mukun;Luo, Xudong;Dai, Xiaopei
通讯作者：
Dai, Xiaopei
DOI：
10.1177/0002716295542001004
发表时间：
1995-11-01
影响因子：
2.8
作者：
BARTOS, OJ
通讯作者：
BARTOS, OJ
影响因子：
13.7
作者：
Camerer, CF;Ho, TH;Chong, JK
通讯作者：
Chong, JK
影响因子：
2.7
作者：
Carneiro, Davide;Novais, Paulo;Neves, Jose
通讯作者：
Neves, Jose
影响因子：
3
作者：
Filzmoser, Michael;Vetschera, Rudolf
通讯作者：
Vetschera, Rudolf