Article

Hierarchical clustering optimizes the tradeoff between compositionality and expressivity of task structures for flexible reinforcement learning

2021-07-21

Abstract excerpt

A hallmark of human intelligence, but challenging for reinforcement learning (RL) agents, is the ability to compositionally generalise, that is, to recompose familiar knowledge components in novel ways to solve new problems. For instance, when navigating in a city, one needs to know the location of the destination and how to operate a vehicle to get there, whether it be pedalling a bike or operating a car. In RL,...

Topics

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

Identifiers and source

Literature Corpus work: 4f727996-b003-5190-97a9-436da4540910
DOI: 10.1101/2021.07.20.453122

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Hierarchical clustering optimizes the tradeoff between compositionality and expressivity of task structures for flexible reinforcement learningDOI 10.1101/2021.07.20.453122Read

Compositional clustering in task structure learningSemantic proximity Read

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

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

Hierarchical Bayesian Models of Reinforcement Learning: Introduction and comparison to alternative methodsSemantic proximity Read

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

Learning Structures: Predictive Representations, Replay, and GeneralizationSemantic proximity Read

Connecting Exploration, Generalization, and Planning in Correlated TreesSemantic proximity Read

Toward the Emergence of Intelligent Control: Episodic Generalization and OptimizationSemantic proximity Read

Preserving and combining knowledge in robotic lifelong reinforcement learningSemantic proximity Read

Compositional generalization in multi-armed banditsSemantic proximity Read

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

Computational neural mechanisms of goal-directed planning and problem solvingSemantic proximity Read