We thank the reviewers for their time and valuable feedback. Below, we clarify several important points raised by the reviewers. An extra page in the final version will allow us to include the requested details. We believe these clarifications, together with new analyses, resolve all key issues raised. Rep'16] and provides a highly constraining measure of local topology.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. Summary ------- The authors study stochastic optimal control problems with incomplete state information. In particular, they consider problems where the sensors are adaptive. They compare sensor configurations which are optimal under a standard signal detection paradigm with sensor configurations that are optimal for a given control problem. Comments -------- Optimal sensor adaptation has a long history in computational neuroscience.

We thank the reviewers for their time and valuable feedback. "scalability is particularly appealing", "theoretical analysis is great, substantial, valid, correct", experiments are We believe these clarifications, together with our new analyses, resolve all key issues raised. As suggested by reviewers, we will carefully discuss this in the final version. We are not claiming novelty in "the idea of using local subgraphs to compute node GNN on an entire graph together with MAML, performs 42.5% worse than G-M's variant is that it uses the's performance can vary with local subgraph size We will include this analysis in our final version. Empirically, we find the subgraph construction takes 14.7% of training time, and this can be's comment of "evaluating each node label individually", we note that each mini-batch consists We will include the full study in the final version. Disjoint Labels" problem, each task defines an N -size label set, and samples K nodes for each label N

Finally, we are also releasing all the code we are able to in order to support reproducibility.