Ouranalysis culminates inshowing thatthere exists a universally consistent histogram-style estimator that converges to any multi-view model with a finite number of Lipschitz continuous components at a rate of eO(1/3 n) in L1 error.

We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward.

We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward.