I am reading the paper A Contextual-Bandit Approach to Personalized News Article Recommendation, where it refers to $\epsilon$-greedy (disjoint) algorithm. I suspect, that it is just a version of a K-armed bandit with regressors that estimate the average reward for an arm. However, I cannot find the description of this algorithm in the literature (papers, books, or other resources)



You must log in to answer this question.