LEARNING WHILE EXPERIMENTING

• 成果类型: Article
• 署名作者: Damiano, Ettore; Li, Hao; Suen, Wing
• 署名单位: University of Toronto; University of British Columbia; University of Hong Kong
• 刊物名称: ECONOMIC JOURNAL
• ISSN/ISSBN: 0013-0133
• DOI: 10.1093/ej/uez043
• 发表日期: 2020
• 页码: 65-92
• 关键词: development competition; Dynamic allocation; MODEL

摘要

An agent performing risky experimentation can benefit from suspending it to learn directly about the state. 'Positive' information acquisition seeks news that would confirm the state that favours experimentation. It is used as a last-ditch effort when the agent is pessimistic about the risky arm before abandoning it. 'Negative' information acquisition seeks news that would demonstrate that experimentation is futile. It is used as an insurance strategy to avoid wasteful experimentation when the agent is still optimistic. A higher reward from risky experimentation expands the region of beliefs that the agent optimally chooses information acquisition rather than experimentation.