.png){kind=icon}
返回
Thompson Sampling for Stochastic Control: The Continuous Parameter Case
.png){kind=icon}
PRE
AI
DOI：10.1109/TAC.2019.2895253.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recently, Thompson sampling has been shown to achieve good theoretical performance guarantees for stochastic control problems with parameter uncertainty when the state, control, and parameter spaces are all finite. Much less is known however about the performance of Thompson sampling when applied to continuous or more general spaces, which constitutes an important class of problems in practice. In this paper, we study Thompson sampling when applied to a broad class of average cost stochastic control problems where the state, control, and parameter spaces are all general measurable spaces. The main contributions of our paper are establishing theoretical performance guarantees for Thompson sampling as measured by: first, expected posterior sampling error; and second, average per period regret.
Keyword:
Average regret bounds
Bayesian learning
general parameter spaces
posterior convergence rate
Thompson sampling
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7
论文数:
1.3W
被引数:
6.7W
机构
引用论文
分享收藏In situ direct observation of photocorrosion in ZnO crystals in ionic liquid using a laser-equipped high-voltage electron microscope使用配备激光的高压电子显微镜原位直接观察离子液体中ZnO晶体的光腐蚀.png)
AIP Advances
OAAI
AIP AdvancesIF0
OAAI分享收藏Post-traumatic inflammatory response: perhaps a succession of phases with a nutritional purpose
PREAI
分享收藏
查看更多内容