Relational reinforcement learning with guided demonstrations

DOI10.1016/J.ARTINT.2015.02.006MaRDI QIDQ2407440zbMATH OpenOpenAlexFDO

Authors Yanyan Li

Publication date 29 September 2017

Published in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.artint.2015.02.006

zbMATH Keywords

active learninglearning guidanceplanning excusereinforcement learningrobot learningteacher demonstrationteacher guidance

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial intelligence for robotics (68T40)

Recommendations

• Integrating guidance into relational reinforcement learning
• Inductive Logic Programming
• scientific article; zbMATH DE number 1775635
• Relational reinforcement learning
• scientific article; zbMATH DE number 1977952
• Exploration in relational domains for model-based reinforcement learning
• Relational reinforcement learning for planning with exogenous effects

Cites work

• 10.1162/153244303765208377
• scientific article; zbMATH DE number 5547890 (Why is no real title available?)
• Interactive policy learning through confidence-based autonomy
• Knows what it knows: a framework for self-aware learning
• Near-optimal reinforcement learning in polynomial time
• The fast downward planning system

Cited in

(7)

• Lifted model checking for relational MDPs
• Active deep Q-learning with demonstration
• Deliberative acting, planning and learning with hierarchical operational models
• Editorial: Towards a science of integrated AI and robotics
• Interactive policy learning through confidence-based autonomy
• Exploration in relational domains for model-based reinforcement learning
• Relational reinforcement learning

Describes a project that uses

Uses Software

• TAMER

This page was built for publication: Relational reinforcement learning with guided demonstrations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2407440)