My research is dedicated to the development of principled algorithms to solve combinatorial search problems. We are currently focused on combinatorial search problems arising from the search for programmatic representations to sequential decision-making problems (e.g., computer programs encoding policies for solving reinforcement learning problems). I believe that the most promising path to creating agents that learn continually, efficiently, and safely is to represent the agents' knowledge programmatically. While programmatic representations offer many advantages, including modularity and reusability, they present a significant challenge: the need to search over large, non-differentiable spaces not suited for gradient descent methods. Addressing this challenge is the current focus of my work.