# Policies.klUCBloglog module¶

The generic kl-UCB policy for one-parameter exponential distributions. By default, it assumes Bernoulli arms. Note: using log(t) + c log(log(t)) for the KL-UCB index of just log(t) Reference: [Garivier & Cappé - COLT, 2011].

Policies.klUCBloglog.c = 3

default value, as it was in pymaBandits v1.0

class Policies.klUCBloglog.klUCBloglog(nbArms, tolerance=0.0001, klucb=CPUDispatcher(<function klucbBern>), c=1.0, lower=0.0, amplitude=1.0)[source]

The generic kl-UCB policy for one-parameter exponential distributions. By default, it assumes Bernoulli arms. Note: using log(t) + c log(log(t)) for the KL-UCB index of just log(t) Reference: [Garivier & Cappé - COLT, 2011].

__str__()[source]

-> str

computeIndex(arm)[source]

Compute the current index, at time t and after $$N_k(t)$$ pulls of arm k:

$\begin{split}\hat{\mu}_k(t) &= \frac{X_k(t)}{N_k(t)}, \\ U_k(t) &= \sup\limits_{q \in [a, b]} \left\{ q : \mathrm{kl}(\hat{\mu}_k(t), q) \leq \frac{\log(t) + c \log(\max(1, \log(t)))}{N_k(t)} \right\},\\ I_k(t) &= U_k(t).\end{split}$

If rewards are in $$[a, b]$$ (default to $$[0, 1]$$) and $$\mathrm{kl}(x, y)$$ is the Kullback-Leibler divergence between two distributions of means x and y (see Arms.kullback), and c is the parameter (default to 1).

computeAllIndex()[source]

Compute the current indexes for all arms, in a vectorized manner.

__module__ = 'Policies.klUCBloglog'