To focus the search input from anywhere on the page, press the 'S' key.
in-package search v0.1.0
The WrapRange functor wraps a bandit algorithm with the doubling trick. This heuristic allows to use a bandit algorithm without knowing the reward ranges. All rewards are linearly rescaled to a range (initially given by a RangeParam). When a value is observed above the range, the bandit algorithm is restarted and the range interval is doubled in that direction.
module R : RangeParam
type bandit = B.bandit
val initialBandit : bandit rangedBandit
val step : bandit rangedBandit -> float -> rangedAction * bandit rangedBandit