| 来源类型 | Discussion paper |
| 规范类型 | 论文 |
| 来源ID | DP14046 |
| DP14046 Undiscounted Bandit Games | |
| R Godfrey Keller; Sven Rady | |
| 发表日期 | 2019-10-08 |
| 出版年 | 2019 |
| 语种 | 英语 |
| 摘要 | We analyze undiscounted continuous-time games of strategic experimentation with two-armed bandits. The risky arm generates payoffs according to a Lévy process with an unknown average payoff per unit of time which nature draws from an arbitrary finite set. Observing all actions and realized payoffs, players use Markov strategies with the common posterior belief about the unknown parameter as the state variable. We show that the unique symmetric Markov perfect equilibrium can be computed in a simple closed form involving only the payoff of the safe arm, the expected current payoff of the risky arm, and the expected full-information payoff, given the current belief. In particular, the equilibrium does not depend on the precise specification of the payoff-generating processes. |
| 主题 | Industrial Organization |
| 关键词 | Strategic experimentation Two-armed bandit Strong long-run average criterion Markov perfect equilibrium Hjb equation Viscosity solution |
| URL | https://cepr.org/publications/dp14046 |
| 来源智库 | Centre for Economic Policy Research (United Kingdom) |
| 资源类型 | 智库出版物 |
| 条目标识符 | http://119.78.100.153/handle/2XGU8XDN/542932 |
| 推荐引用方式 GB/T 7714 | R Godfrey Keller,Sven Rady. DP14046 Undiscounted Bandit Games. 2019. |
| 条目包含的文件 | 条目无相关文件。 | |||||
| 个性服务 |
| 推荐该条目 |
| 保存到收藏夹 |
| 导出为Endnote文件 |
| 谷歌学术 |
| 谷歌学术中相似的文章 |
| [R Godfrey Keller]的文章 |
| [Sven Rady]的文章 |
| 百度学术 |
| 百度学术中相似的文章 |
| [R Godfrey Keller]的文章 |
| [Sven Rady]的文章 |
| 必应学术 |
| 必应学术中相似的文章 |
| [R Godfrey Keller]的文章 |
| [Sven Rady]的文章 |
| 相关权益政策 |
| 暂无数据 |
| 收藏/分享 |
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
