Suppr超能文献

辛普森悖论的一个新结果:来自个人主义学习者群体的一次性囚徒困境中的稳定合作。

A new consequence of Simpson's paradox: stable cooperation in one-shot prisoner's dilemma from populations of individualistic learners.

作者信息

Chater Nick, Vlaev Ivo, Grinberg Maurice

机构信息

Department of Psychology, University College London, London, United Kingdomn.

出版信息

J Exp Psychol Gen. 2008 Aug;137(3):403-21. doi: 10.1037/0096-3445.137.3.403.

Abstract

Theories of choice in economics typically assume that interacting agents act individualistically and maximize their own utility. Specifically, game theory proposes that rational players should defect in one-shot prisoners' dilemmas (PD). Defection also appears to be the inevitable outcome for agents who learn by reinforcement of past choices, because whatever the other player does, defection leads to greater reinforcement on each trial. In a computer simulation and 4 experiments, the authors show that, apparently paradoxically, when players' choices are correlated by an exogenous factor (here, the cooperativeness of the specific PD chosen), people obtain greater average reinforcement for cooperating, which can sustain cooperation. This effect arises from a well-known statistical paradox, Simpson's paradox. The authors speculate that this effect may be relevant to aspects of real-world human cooperative behavior.

摘要

经济学中的选择理论通常假定,相互作用的主体以个体主义方式行事,并使自身效用最大化。具体而言,博弈论提出,理性参与者在一次性囚徒困境中应选择背叛。对于通过强化过去的选择来学习的主体而言,背叛似乎也是必然结果,因为无论其他参与者怎么做,在每次试验中背叛都会带来更大的强化。在一项计算机模拟和四项实验中,作者表明,看似自相矛盾的是,当参与者的选择因一个外生因素(此处为所选择的特定囚徒困境的合作性)而相关联时,人们通过合作能获得更大的平均强化,这可以维持合作。这种效应源于一个著名的统计悖论——辛普森悖论。作者推测,这种效应可能与现实世界中人类合作行为的各个方面相关。

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验