Planning in high-dimensional space remains a challenging problem, even with recent advances in algori
thms and computational power. Our aim is to allow agents to form mental models of their environments for planning. Building on insights gained from knowledge distillation methods, we choose as our features the outputs of a pre-trained network, yielding a compressed representation of the current state. The representation is chosen such that it allows for fast search using classical graph search algorithms. We display the effectiveness of our approach on a viewpoint-matching task using a modified best-first search algorithm.