Article

Episodic Control as Meta-Reinforcement Learning

2018-07-03

Abstract excerpt

Recent research has placed episodic reinforcement learning (RL) alongside model-free and model-based RL on the list of processes centrally involved in human reward-based learning. In the present work, we extend the unified account of model-free and model-based RL developed by Wang et al. (2018) to further integrate episodic learning. In this account, a generic model-free “meta-learner” learns to deploy and coordin...

Topics

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

Identifiers and source

Literature Corpus work: f2c7b937-07a3-5e98-b696-9f83d7360e41
DOI: 10.1101/360537

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Episodic Control as Meta-Reinforcement LearningDOI 10.1101/360537Read

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

From Reinforcement Learning to Cognitive Psychology: with Navigational Strategies in MindSemantic proximity Read

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

Hybrid Neural-Cognitive Models Reveal Flexible Context-Dependent Information Processing in Reversal LearningSemantic proximity Read

Imitation as a model-free process in human reinforcement learningSemantic proximity Read

Multi-Task Reinforcement Learning in HumansSemantic proximity Read

The Role of Executive Function in Shaping Reinforcement LearningSemantic proximity Read

Learning and Forgetting Using Reinforced Bayesian Change DetectionSemantic proximity Read

On the computational principles underlying human explorationSemantic proximity Read

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

Flexible working memory through selective gating and attentional taggingSemantic proximity Read

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