Functor Obandit.MakeAlphaPhiUCB

module MakeAlphaPhiUCB: functor (P : AlphaPhiUCBParam) -> Bandit  with type bandit = banditEstimates

The $(\alpha,\psi)$-UCB Bandit for stochastic regret minimization described in [1].

Parameters:

P : AlphaPhiUCBParam

type bandit

The internal data structure of the bandit algorithm.

val initialBandit : bandit

The initial state of the bandit algorithm.

val step : bandit -> float -> int * bandit

step r advances the bandit game one step, where r is the reward for the last action. The result of this call is the next action, encoded as an integer in $ \{ 0, \cdots , K-1 \} $, and the new state of the bandit. The reward range depends on the bandit algorithm in use and the first reward provided to the algorithm is discarded.