Abstraction from demonstration for efficient reinforcement learning in high-dimensional domains

DOI10.1016/J.ARTINT.2014.07.003zbMATH Open1405.68283OpenAlexW1965568826MaRDI QIDQ460616FDOQ460616

Authors: Luis C. Cobo, Kaushik Subramanian, Charles L. jun. Isbell, Aaron D. Lanterman, Andrea L. Thomaz 

Publication date: 13 October 2014

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.artint.2014.07.003

Recommendations

• Efficient abstraction selection in reinforcement learning
• Automatic complexity reduction in reinforcement learning
• AI 2005: Advances in Artificial Intelligence
• Kernel dynamic policy programming: applicable reinforcement learning to robot systems with high dimensional states
• From skills to symbols: learning symbolic representations for abstract high-level planning

zbMATH Keywords

dimensionality reductionreinforcement learningfunction approximationlearning from demonstration

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Scikit-learn: machine learning in Python
• Recent advances in hierarchical reinforcement learning
• Programming backgammon using self-teaching neural nets
• 10.1162/1532443041827907
• Reducing reinforcement learning to KWIK online regression
• Algorithms for reinforcement learning.
• Title not available (Why is that?)
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Title not available (Why is that?)
• ML-KNN: A lazy learning approach to multi-label learning
• Title not available (Why is that?)
• Evolutionary function approximation for reinforcement learning
• Title not available (Why is that?)
• Efficient abstraction selection in reinforcement learning

Cited In (6)

• Automatic complexity reduction in reinforcement learning
• AI 2005: Advances in Artificial Intelligence
• Qualitative spatial abstraction in reinforcement learning. Foreword by Christian Freksa.
• From skills to symbols: learning symbolic representations for abstract high-level planning
• Efficient abstraction selection in reinforcement learning
• Title not available (Why is that?)

Uses Software

• Scikit
• C4.5
• ML-KNN

This page was built for publication: Abstraction from demonstration for efficient reinforcement learning in high-dimensional domains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q460616)