Interactive policy learning through confidence-based autonomy

MaRDI QIDQ3624174zbMATH OpenFDO

Authors

Publication date 28 April 2009

Full work available at URL https://arxiv.org/abs/1401.3439

zbMATH Keywords

Confident ExecutionCorrective Demonstration

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonnumerical algorithms (68W05)

Recommendations

• Relational reinforcement learning with guided demonstrations
• scientific article; zbMATH DE number 2118236
• Bayesian policy reuse
• Methods for learning control policies from variable-constraint demonstrations
• Safety-aware apprenticeship learning

Cited in

(9)

• Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs
• Policy space identification in configurable environments
• Learning perceptually grounded word meanings from unaligned parallel data
• Relational reinforcement learning with guided demonstrations
• Relational reinforcement learning for planning with exogenous effects
• scientific article; zbMATH DE number 7370547 (Why is no real title available?)
• Competence-aware systems
• A human-robot collaborative reinforcement learning algorithm
• Reinforcement learning

This page was built for publication: Interactive policy learning through confidence-based autonomy

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3624174)