Strategic experimentation
Strategic experimentation
复制标题
DOI：
10.1111/1468-0262.00022
复制
发表时间：
1999-03-01
期刊：
影响因子：
6.1
通讯作者：
Harris, C
中科院分区：
文献类型：
--
作者：
Bolton, P;Harris, C
本文将经典的双臂强盗问题扩展到一个多智能体设置，其中N个参与者每个都面临相同的实验问题。单智能体问题的主要变化是智能体现在可以从其他智能体的当前实验中学习。因此，信息是一种公共产品，在实验中自然会出现搭便车的问题。更有趣的是，其他人未来进行实验的前景会鼓励代理人增加当前的实验，以便提前获得由此类实验产生的额外信息。本文从搭便车效应和鼓励效应的角度对平稳马尔可夫均衡集进行了分析。
This paper extends the classic two-armed bandit problem to a many-agent setting in which N players each face the same experimentation problem. The main change from the single-agent problem is that an agent can now learn from the current experimentation of other agents. Information is therefore a public good, and a free-rider problem in experimentation naturally arises. More interestingly, the prospect of future experimentation by others encourages agents to increase current experimentation, in order to bring forward the time at which the extra information generated by such experimentation becomes available. The paper provides an analysis of the set of stationary Markov equilibria in terms of the free-rider effect and the encouragement effect.