Batch mode reinforcement learning based on the synthesis of artificial trajectories

DOI10.1007/s10479-012-1248-5zbMath1276.68134WikidataQ42258641 ScholiaQ42258641MaRDI QIDQ378762

Damien Ernst, Louis Wehenkel, Raphael Fonteneau, Susan A. Murphy

Publication date: 12 November 2013

Published in: Annals of Operations Research (Search for Journal in Brave)

Full work available at URL: http://europepmc.org/articles/pmc3773886

zbMATH Keywords

optimal control; reinforcement learning; function approximators; artificial trajectories

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

93E35: Stochastic learning and adaptive control

Related Items

Lipschitzness is all you need to tame off-policy generative adversarial imitation learning

Uses Software

• Approxrl

Cites Work

• Kernel-based reinforcement learning
• Technical update: Least-squares temporal difference learning
• Least squares policy evaluation algorithms with linear function approximation
• Towards Min Max Generalization in Reinforcement Learning
• Marginal Mean Models for Dynamic Regimes
• Optimal Dynamic Treatment Regimes
• A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect
• 10.1162/1532443041827907
• Machine Learning: ECML 2003
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item