突破传统贝叶斯框架，设计更鲁棒的激励探索机制
On Incentivized Exploration beyond Bayesianism and Full-Information
- 引入非贝叶斯视角，允许代理拥有主方未知的外部信息
- 提出合理（非占优）行动选择的新定义，处理策略僵局
- 适用于无共同先验、仅知奖励分布属于一组可能先验的场景
我们拓展了Kremer等人[2014]提出的贝叶斯全信息设定下的激励相容探索。考虑代理可能持有主方未知的外部信息的情形。我们表明此类设定需要新的激励探索概念，且必须超越贝叶斯视角。为此，我们引入一种新定义：代理可选择任意合理的（非占优）行动。此外，该框架对平局情况具有更强的鲁棒性，并可扩展至代理不共享单一共同先验，而仅知奖励分布属于一组潜在先验的情况。
原文摘要 · Abstract (English)
We extend Incentive Compatible Exploration beyond the Bayesian full-information setting of Kremer et al. [2014]. We consider agents that may possess external information unknown to the principal. We show such settings require new notions of incentivized exploration, as well as going beyond a Bayesian perspective, and we introduce a definition where agents choose any reasonable (undominated) action. Furthermore, our framework provides for a more robust treatment of ties, and extends to settings where agents lack a single common prior and instead only know that reward distributions belong to a collection of potential priors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。