Further clarify the description of the reduction from fair online batch classification to online batch classification.

We consider online learning in episodic loop-free Markov decision processes (MDPs), where the loss function can change arbitrarily between episodes.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. Online Learning with Costly Features and Labels Summary: The paper discusses a version of sequential prediction where there is a cost associated to obtaining features and labels. First, the case where labels are given but features are bought. Here the regret bound is of the form sqrt{2^d T}. The time dependence is as desired, and a lower bound shows that the exponential dependence in the dimension of the features space cannot be reduced in general.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper presents a probabilistic model for language learning. The authors cover the nature in which a pair of cooperative agents may work together to create an agreed-upon language. One question I have is how this could possibly be implemented in real-world language learning situations. Your evaluation of the emergence of phenomenon seen in real world languages makes me think you are trying to model or learn something about what real world language evolution is like.

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