Abstraction in data-sparse task transfer

DOI10.1016/J.ARTINT.2021.103551MaRDI QIDQ2238727zbMATH OpenOpenAlexFDO

Authors Tesca Fitzgerald, Ashok K. Goel, Andrea L. Thomaz

Publication date 2 November 2021

Published in Artificial Intelligence (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1016/j.artint.2021.103551

zbMATH Keywords

abstractioncognitive roboticsinteractive robot learningtask representationtask transfer

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Recommendations

• Evolving static representations for task transfer
• Task-specific loss: a teacher-centered approach to transfer learning between distinctly structured robotic agents
• Cooperation of categorical and behavioral learning in a practical solution to the abstraction problem
• Transfer learning via advice taking
• From skills to symbols: learning symbolic representations for abstract high-level planning

Cites work

• Dynamical movement primitives: learning attractor models for motor behaviors
• The structure-mapping engine: Algorithm and examples
• Transfer learning for reinforcement learning domains: a survey

Cited in

(3)

• Task-specific loss: a teacher-centered approach to transfer learning between distinctly structured robotic agents
• Evolving static representations for task transfer
• Cooperation of categorical and behavioral learning in a practical solution to the abstraction problem

This page was built for publication: Abstraction in data-sparse task transfer

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2238727)