Export Reviews, Discussions, Author Feedback and Meta-Reviews

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper presents an interesting idea of using a robust formulation to fit a value function given aggregate states. The robust formulation leads to a much stronger error bound than what is achieved by regular approximate value iteration. The key is in using the algorithm to effectively select weights applied to states within each aggregate. On the negative side, the authors do not do a good job at presenting their notation and algorithm in a clear way, and the computational results are difficult to understand.