First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. Summary: This paper provides a Bayesian expected regret bound for the Posterior Sampling for the Reinforcement Learning (PSRL) algorithm. PSRL has been introduced by [Strens2000], and can be seen as the application of Thompson sampling for RL problems: a model is sampled from the (posterior) distribution over models, the optimal policy for the sampled model is calculated, the policy is followed until the end of the horizon, and the distribution over models is updated. PSRL for finite MDPs has been analyzed by [OVRR2013], but the main contribution of this paper is to analyze PSRL for MDPs with general state and action space. In the analysis, the authors use the concept of eluder dimension introduced by [RVR2013]. Eluder dimension was previously used in the analysis of bandit problems (for both Thompson Sampling and the Optimism in Face of Uncertainty (OFU) approaches).

In contiguous LWCV we leave out contiguous blocks from a time series.

In the present work, we address (i) by extending ACV to CV schemes with dependence structure between the folds.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper presents two very natural methods for searching for Bayesian networks of treewidth <= k. The exact method uses a MILP to search jointly over (Bayesian network, elimination order, chordal graph induced by elimination on the moralized network). The approximate method repeatedly samples a random k-tree and then uses dynamic programming or sampling to find the best network whose moralization is a subgraph of the k-tree (any network of treewidth <= k can be obtained in this way). The paper is clear and the methods seem like textbook material.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task.