Provable Hierarchical Lifelong Learning with a Sketch-based Modular Architecture
This addresses the challenge of efficient and scalable lifelong learning in AI, though it appears incremental as it builds on prior modular and hierarchical approaches.
The paper tackles the problem of lifelong learning for hierarchically structured tasks by proposing a modular architecture, proving it can theoretically learn tasks using previously learned tasks as subroutines, and empirically showing it outperforms standard methods on tasks that are otherwise not efficiently learnable.
We propose a modular architecture for the lifelong learning of hierarchically structured tasks. Specifically, we prove that our architecture is theoretically able to learn tasks that can be solved by functions that are learnable given access to functions for other, previously learned tasks as subroutines. We empirically show that some tasks that we can learn in this way are not learned by standard training methods in practice; indeed, prior work suggests that some such tasks cannot be learned by any efficient method without the aid of the simpler tasks. We also consider methods for identifying the tasks automatically, without relying on explicitly given indicators.