- Abstract: We consider learning to generalize and extrapolate with limited data to harder compositional problems than a learner has previously seen. We take steps toward this challenge by presenting a characterization, algorithm, and implementation of a learner that programs itself automatically to reflect the structure of the problem it faces. Our key ideas are (1) transforming representations with modular units of computation is a solution for decomposing problems in a way that reflects their subproblem structure; (2) learning the structure of a computation can be formulated as a sequential decision-making problem. Experiments on solving various multilingual arithmetic problems demonstrate that our method generalizes out of distribution to unseen problem classes and extrapolates to harder versions of the same problem. Our paper provides the first element of a framework for learning general-purpose, compositional and recursive programs that design themselves.
- TL;DR: We present a learner that learns the structure and parameters of a program that dynamically customizes itself to the problem instance.
- Keywords: compositionality, recursion, program induction, re-representation, reinforcement learning, metareasoning, self-organizing neural networks