Article

Temporal and state abstractions for efficient learning, transfer and composition in humans

2020-02-24

Abstract excerpt

Humans use prior knowledge to efficiently solve novel tasks, but how they structure past knowledge to enable such fast generalization is not well understood. We recently proposed that hierarchical state abstraction enabled generalization of simple one-step rules, by inferring context clusters for each rule. However, humans’ daily tasks are often temporally extended, and necessitate more complex multi-step, hierarc...

Topics

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

Identifiers and source

Literature Corpus work: b52efb31-4e8b-5896-895c-5d4ca9aa45cf
DOI: 10.1101/2020.02.20.958587

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Temporal and state abstractions for efficient learning, transfer and composition in humansDOI 10.1101/2020.02.20.958587Read

Multi-Task Reinforcement Learning in HumansSemantic proximity Read

Computational Evidence for Hierarchically-Structured Reinforcement Learning in HumansSemantic proximity Read

Compositional generalization in multi-armed banditsSemantic proximity Read

Deterministic response strategies in trial-and-error learningSemantic proximity Read

Generalizing to generalize: when (and when not) to be compositional in task structure learningSemantic proximity Read

Long short-term prediction guides human metacognitive reinforcement learningSemantic proximity Read

Meta-learning attentional strategies in multidimensional reinforcement learningSemantic proximity Read

Assembling hierarchies of action using sequencing and abstraction: studies and models of zero-shot learningSemantic proximity Read

Simple Plans or Sophisticated Habits? State, Transition and Learning Interactions in the Two-step TaskSemantic proximity Read

Reward-predictive representations generalize across tasks in reinforcement learningSemantic proximity Read

The Value of AbstractionSemantic proximity Read

Assembling hierarchies of action using sequencing and abstraction: studies and models of zero-shot learningSemantic proximity Read