This paper proposes a hierarchical method for representation learning and goal-directed search in morphogenetic systems, and is evaluated on a particular type of cellular automata (Lenia). This method allows for identifying diverse and “interesting” regions of space in the dynamical system, also supporting small amounts of human feedback to identifying preferred regions of space. R1 and R4 praised the novelty of this approach, with R3 also finding it interesting and highlighting its implications for other areas of research. The reviews initially had some concerns with clarity, but these were satisfactorily addressed by the rebuttal. Another issue, highlighted by R1 and R4, was that the system has only been evaluated on a single dynamical system, and so its applicability to other domains is unclear. I found the paper quite interesting and unique, and believe it will be very thought-provoking and interesting to the NeurIPS community. While I agree that it would be good to see a demonstration of the system in other domains, the paper as it stands is an important contribution in and of itself, with many new ideas. I therefore recommend acceptance.