Supplementary material is at the end of this document.

Decision Process (MDP) setting where the reward function is not given, but demonstrations from experts are available. Although the goal of imitation learning is to learn a policy that produces behaviors nearly as good as the experts' for a desired task, assumptions of consistent optimality for demonstrated behaviors are often violated in practice.

LLP, prove generalization error bounds associated to two bag generation models, and establish universal consistency with respect to the balanced error rate (BER).

The multiple-try Metropolis (MTM) algorithm is an extension of the Metropolis-Hastings (MH) algorithm by selecting the proposed state among multiple trials according to some weight function. Although MTM has gained great popularity owing to its faster empirical convergence and mixing than the standard MH algorithm, its theoretical mixing property is rarely studied in the literature due to its complex proposal scheme.