The Confidence Bound Target (CBT) algorithm is designed for infinite arms bandit problem. It is shown that CBT algorithm achieves the regret lower bound for general reward distributions. Reference: Hock Peng Chan and Shouri Hu (2018) <arXiv:1805.11793>.
https://anaconda.org/r/r-cbt/badges/version.svg
https://anaconda.org/r/r-cbt/badges/latest_release_date.svg
https://anaconda.org/r/r-cbt/badges/latest_release_relative_date.svg
https://anaconda.org/r/r-cbt/badges/platforms.svg
https://anaconda.org/r/r-cbt/badges/license.svg
https://anaconda.org/r/r-cbt/badges/downloads.svg