Article

Compositional generalization in multi-armed bandits

2021-05-14

Abstract excerpt

<p>To what extent do human reward learning and decision-making rely on the ability to represent and generate richly structured relationships between options? We provide evidence that structure learning and the principle of compositionality play crucial roles in human reinforcement learning. In a new multi-armed bandit paradigm, we found evidence that participants are able to learn representations of different rewa...

Topics

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

Identifiers and source

Literature Corpus work: 771f0900-4334-5dff-8874-a17213abd819
DOI: 10.31234/osf.io/v6mzb

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Compositional generalization in multi-armed banditsDOI 10.31234/osf.io/v6mzbRead

Finding structure in multi-armed banditsSemantic proximity Read

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

Towards a unifying theory of generalizationSemantic proximity Read

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

Multi-Task Reinforcement Learning in HumansSemantic proximity Read

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

Searching for rewards in graph-structured spacesSemantic proximity Read

Meta-learning attentional strategies in multidimensional reinforcement learningSemantic proximity Read

The Role of Executive Function in Shaping Reinforcement LearningSemantic proximity Read

Using Deep Learning to Predict Human Decisions, and Cognitive Models to Explain Deep Learning ModelsSemantic proximity Read

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

Context-dependent outcome encoding in human reinforcement learningSemantic proximity Read