Genetic algorithms are a class of algorithms in reinforcement learning that use models inspired from evolutionary processes to help computers learn to solve complex problems. Different solution strategies are modeled as individuals in a population, which are allowed to evolve through an iterative process aimed at maximizing a given fitness function. These algorithms have been shown to be adept at solving problems in a variety of different fields. In this talk we will explore uses of genetic algorithms for solving computationally complex problems in low-dimensional topology and knot theory.