Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots

DOI10.1016/J.ARTINT.2015.02.001zbMath1420.68213OpenAlexW2083954950MaRDI QIDQ2407444

Matthew Luciw, Varun Raj Kompella, Jürgen Schmidhuber, Marijn Stollenga

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.2015.02.001

zbMATH Keywords

reinforcement learningincremental learningcontinual learningslow feature analysisskill acquisitionartificial curiosityiCub

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Machine vision and scene understanding (68T45) Artificial intelligence for robotics (68T40)

Related Items (3)

Editorial: Towards a science of integrated AI and robotics ⋮ Optimal Curiosity-Driven Modular Incremental Slow Feature Analysis ⋮ Slowness as a Proxy for Temporal Predictability: An Empirical Comparison

Cites Work

• Independent component analysis, a new concept?
• CHILD: A first step towards continual learning
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Principal component analysis.
• Convergence analysis of a simple minor component analysis algorithm
• Incremental Slow Feature Analysis: Adaptive Low-Complexity Slow Feature Updating from High-Dimensional Input Streams
• On the Relation of Slow Feature Analysis and Laplacian Eigenmaps
• Training Products of Experts by Minimizing Contrastive Divergence
• Slow Feature Analysis: Unsupervised Learning of Invariances
• 10.1162/1532443041827907
• Learning the parts of objects by non-negative matrix factorization
• Self-organizing maps.
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots