Article

Generalizing to generalize: when (and when not) to be compositional in task structure learning

2019-02-12

Abstract excerpt

Humans routinely face novel environments in which they have to generalize in order toact adaptively. However, doing so involves the non-trivial challenge of deciding which aspects of a task domain to generalize. While it is sometimes appropriate to simply re-use a learned behavior, often adaptive generalization entails recombining distinct components of knowledge acquired across multiple contexts. Theoretical work...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: ad0c5a8f-6ae0-5175-901d-50f11f5ead72
DOI: 10.1101/547406

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Generalizing to generalize: when (and when not) to be compositional in task structure learningDOI 10.1101/547406Read

Towards a unifying theory of generalizationSemantic proximity Read

Unifying principles of generalization: past, present, and futureSemantic proximity Read

Temporal and state abstractions for efficient learning, transfer and composition in humansSemantic proximity Read

Environment-sensitive generalization and exploration strategiesSemantic proximity Read

The Generalization Artist - Or: How Can We Characterize Human Generalization?Semantic proximity Read

Compositional clustering in task structure learningSemantic proximity Read

Compositional generalization in multi-armed banditsSemantic proximity Read

Meta-learning attentional strategies in multidimensional reinforcement learningSemantic proximity Read

How Can We Characterize Human Generalization and Distinguish it from Generalization in Machines?Semantic proximity Read