Review for NeurIPS paper: Compact task representations as a normative model for higher-order brain activity

Weaknesses: One main problem is that the paper does not contain a plausible method for learning. Not only would this likely be extremely hard (for the informational measures), but there could also be a complex interaction between things like compression, exploration and learning. Although it is certainly interesting to think about the difference between model-based and model-free representations, I wasn't completely convinced by the arguments in the paper. If I understand correctly, the habitual agent would have a partly open-loop character to it (ie it would ignore parts of the observation) - this is dangerous in anything but a completely stationary world; and since animals seem to continue to possess their model-based methods even after control has become habitized, it would also seem that the suggestion would be that animals would maintain two separate representations, one MB and the other MF, which seems wasteful. The experiments could also have been more convincing.