Neural network models of learning and categorization in multigame experiments.

Neural network models of learning and categorization in multigame experiments.
复制标题

DOI:
10.3389/fnins.2011.00139
复制
发表时间:
2011
影响因子:
4.3
通讯作者:
Warglien M
Warglien M
中科院分区:
医学2区
文献类型:
--
作者:
Marchiori D;Warglien M

文献摘要

参考文献

被引文献

相似文献

先前的研究表明,后悔驱动的神经网络可以非常好地预测重复的完全混合游戏中的行为,基本上与最准确的既定学习模型的性能相当。这一结果提出了一个问题:通过神经网络进行建模学习的附加价值是什么。我们认为,这种建模方法允许模型能够区分不同的支付结构并对其做出不同的反应。此外,游戏的分类过程是由这些模型隐式执行的,因此不需要任何外部明确的游戏之间相似性理论。为了验证我们的主张,我们设计并运行了两个多游戏实验,其中受试者以随机顺序面对两个完全混合的 2 × 2 游戏的不同实例。然后,我们在实验数据上测试了两个后悔驱动的神经网络模型,并将它们的性能与其他已建立的学习和纳什均衡模型的性能进行了比较。
Previous research has shown that regret-driven neural networks predict behavior in repeated completely mixed games remarkably well, substantially equating the performance of the most accurate established models of learning. This result prompts the question of what is the added value of modeling learning through neural networks. We submit that this modeling approach allows for models that are able to distinguish among and respond differently to different payoff structures. Moreover, the process of categorization of a game is implicitly carried out by these models, thus without the need of any external explicit theory of similarity between games. To validate our claims, we designed and ran two multigame experiments in which subjects faced, in random sequence, different instances of two completely mixed 2 × 2 games. Then, we tested on our experimental data two regret-driven neural network models, and compared their performance with that of other established models of learning and Nash equilibrium.
DOI: 10.1038/nature04766
发表时间: 2006-06-15
期刊: NATURE
影响因子: 64.8
作者:
Daw, Nathaniel D.;O'Doherty, John P.;Dayan, Peter;Seymour, Ben;Dolan, Raymond J.
通讯作者: Dolan, Raymond J.
DOI: 10.1002/bdm.683
发表时间: 2010-01-01
影响因子: 2
作者:
Erev, Ido;Ert, Eyal;Lebiere, Christian
通讯作者: Lebiere, Christian
DOI: 10.1002/bdm.556
发表时间: 2007-07-01
影响因子: 2
作者:
Ert, Eyal;Erev, Ido
通讯作者: Erev, Ido
DOI: 10.1287/mnsc.29.4.447
发表时间: 1983-01-01
期刊: MANAGEMENT SCIENCE
影响因子: 5.4
作者:
FRIEDMAN, D
通讯作者: FRIEDMAN, D
DOI: 10.1257/000282803321947056
发表时间: 2003-05-01
影响因子: 10.7
作者:
Cooper, DJ;Kagel, JH
通讯作者: Kagel, JH