Improving reinforcement learning by using sequence trees

DOI10.1007/S10994-010-5182-YMaRDI QIDQ1959629zbMATH OpenOpenAlexFDO

Authors Sertan Girgin, Faruk Polat, Reda Alhajj

Publication date 7 October 2010

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-010-5182-y

zbMATH Keywords

conditionally terminating sequencesoptionsreinforcement learningsemi-Markov decision processestemporal abstractions

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Probabilistic inference for determining options in reinforcement learning
• scientific article; zbMATH DE number 2070740
• Advances in Artificial Intelligence – SBIA 2004
• Adaptive representations for reinforcement learning.
• scientific article; zbMATH DE number 2086978

Cites work

• \({\mathcal Q}\)-learning
• Accelerating autonomous learning by using heuristic selection of actions
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• scientific article; zbMATH DE number 3126094 (Why is no real title available?)
• scientific article; zbMATH DE number 1560499 (Why is no real title available?)
• scientific article; zbMATH DE number 1931843 (Why is no real title available?)
• scientific article; zbMATH DE number 2086978 (Why is no real title available?)
• scientific article; zbMATH DE number 2086996 (Why is no real title available?)
• Recent advances in hierarchical reinforcement learning

Cited in

(4)

• scientific article; zbMATH DE number 5957269 (Why is no real title available?)
• Probabilistic inference for determining options in reinforcement learning
• scientific article; zbMATH DE number 2070740 (Why is no real title available?)
• GENERATING EFFECTIVE INITIATION SETS FOR SUBGOAL-DRIVEN OPTIONS

Describes a project that uses

Uses Software

• Soccer server

This page was built for publication: Improving reinforcement learning by using sequence trees

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1959629)