Provable hierarchical lifelong learning with a sketch-based modular architecture
We propose a modular architecture for 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 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 \emph{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.
Code (0)
등록된 구현이 없습니다.
Tasks
Lifelong learningSimilar Papers 제목 키워드 기반
Model Primitive Hierarchical Lifelong Reinforcement Learning
Learning interpretable and transferable subpolicies and performing task decomposition from a single, complex task is difficult. Some traditional hierarchical reinforcement learning techniques enforce this decomposition i…
Hierarchical Reinforcement LearningLifelong learningMeta-Learningmodel+3Provable Hierarchy-Based Meta-Reinforcement Learning
Hierarchical reinforcement learning (HRL) has seen widespread interest as an approach to tractable learning of complex modular behaviors. However, existing work either assume access to expert-constructed hierarchies, or …
DiversityHierarchical Reinforcement LearningLearning TheoryMeta-Learning+4A Deep Hierarchical Approach to Lifelong Learning in Minecraft
We propose a lifelong learning system that has the ability to reuse and transfer knowledge from one task to another while efficiently retaining the previously learned knowledge-base. Knowledge is transferred by learning …
Deep Reinforcement LearningLifelong learningMinecraftReinforcement LearningLifelong Learning with Sketched Structural Regularization
Preventing catastrophic forgetting while continually learning new tasks is an essential problem in lifelong learning. Structural regularization (SR) refers to a family of algorithms that mitigate catastrophic forgetting …
Continual LearningLifelong learningPermuted-MNISTHow does the Mind store Information?
How we store information in our mind has been a major intriguing open question. We approach this question not from a physiological standpoint as to how information is physically stored in the brain, but from a conceptual…
Open-Ended Question Answering