Metalearning, task generalization, transfer learning, and one-shot learning have all shown to be closely related and essential features of broader and more powerful machine learning methodologies. Behind these issues lies a failure of appropriate world-modeling behavior through symbolic abstraction. We seek to offer a possible methodology that facilitates a more robust form of general abstract reasoning, using program induction to facilitate symbolic reasoning. In pursuit of this goal, we explore applications of this paradigm to a block-stacking environment demanding robust physical intuition, with tasks requiring challenging hierarchical planning.

“I hope that through this SuperUROP project, I will learn how to write a publication for an academic conference. Before this, I’ve had multiple research opportunities in machine learning and the application of neural networks, but none have led to a tangible publication. I am excited to explore a more novel area of deep learning and work towards tangible products that demonstrate my research experience and prepare me for graduate-level study.”