Article

Reward-predictive representations generalize across tasks in reinforcement learning

2019-05-30

Abstract excerpt

In computer science, reinforcement learning is a powerful framework with which artificial agents can learn to maximize their performance for any given Markov decision process (MDP). Advances over the last decade, in combination with deep neural networks, have enjoyed performance advantages over humans in many difficult task settings. However, such frameworks perform far less favorably when evaluated in their abili...

Topics

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

Identifiers and source

Literature Corpus work: 68748fa6-ba6f-52b7-a8f6-fcc69d2ccda6
DOI: 10.1101/653493

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Reward-predictive representations generalize across tasks in reinforcement learningDOI 10.1101/653493Read

Discovery and consolidation of analogous reward structure supports generalization in humansSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read

Multi-Task Reinforcement Learning in HumansSemantic proximity Read

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

Compositional generalization in multi-armed banditsSemantic proximity Read

Hierarchical clustering optimizes the tradeoff between compositionality and expressivity of task structures for flexible reinforcement learningSemantic proximity Read

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

Preserving and combining knowledge in robotic lifelong reinforcement learningSemantic proximity Read

Advances in deep reinforcement learning enable better predictions of human behavior in time-continuous tasksSemantic proximity Read

Compositional clustering in task structure learningSemantic proximity Read