Batch mode reinforcement learning based on the synthesis of artificial trajectories

DOI10.1007/S10479-012-1248-5MaRDI QIDQ378762zbMATH OpenOpenAlexWikidataFDO

Authors R. Fonteneau, Louis Wehenkel, D. Ernst, 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 controlreinforcement learningartificial trajectoriesfunction approximators

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic learning and adaptive control (93E35)

Recommendations

• Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path
• scientific article; zbMATH DE number 5957269
• Machine Learning: ECML 2004
• Iteratively extending time horizon reinforcement learning.
• Min max generalization for deterministic batch mode reinforcement learning: relaxation schemes

Cites work

• scientific article; zbMATH DE number 5957269 (Why is no real title available?)
• scientific article; zbMATH DE number 3126094 (Why is no real title available?)
• 10.1162/1532443041827907
• A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect
• Finite-sample analysis of least-squares policy iteration
• Finite-time bounds for fitted value iteration
• Iteratively extending time horizon reinforcement learning.
• Kernel-based reinforcement learning
• Least squares policy evaluation algorithms with linear function approximation
• Linear least-squares algorithms for temporal difference learning
• Marginal Mean Models for Dynamic Regimes
• Optimal Dynamic Treatment Regimes
• Technical update: Least-squares temporal difference learning
• Towards min max generalization in reinforcement learning

Cited in

(4)

• The Bottleneck Simulator: A Model-Based Deep Reinforcement Learning Approach
• Machine Learning: ECML 2004
• Lipschitzness is all you need to tame off-policy generative adversarial imitation learning
• Min max generalization for deterministic batch mode reinforcement learning: relaxation schemes

Describes a project that uses

Uses Software

• Approxrl

This page was built for publication: Batch mode reinforcement learning based on the synthesis of artificial trajectories

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q378762)