Yingfei Wang, Warren B. Powell. Finite-Time Analysis for the Knowledge-Gradient Policy. SIAM J. Control and Optimization, 56(2):1105-1129, 2018. [doi]
@article{WangP18-4,
title = {Finite-Time Analysis for the Knowledge-Gradient Policy},
author = {Yingfei Wang and Warren B. Powell},
year = {2018},
doi = {10.1137/16M1073388},
url = {https://doi.org/10.1137/16M1073388},
researchr = {https://researchr.org/publication/WangP18-4},
cites = {0},
citedby = {0},
journal = {SIAM J. Control and Optimization},
volume = {56},
number = {2},
pages = {1105-1129},
}