Knows what it knows: a framework for self-aware learning

DOI10.1007/s10994-010-5225-4zbMath1237.68154MaRDI QIDQ413843

Alexander L. Strehl, Thomas J. Walsh, Michael L. Littman, Lihong Li

Publication date: 8 May 2012

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-010-5225-4

zbMATH Keywords

computational learning theory; reinforcement learning; active learning; exploration; knows what it knows (KWIK); mistake bound; probably approximately correct (PAC)

Mathematics Subject Classification ID

68Q32: Computational learning theory

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Unnamed Item, Unnamed Item, Consistency of plug-in confidence sets for classification in semi-supervised learning, Adaptive aggregation for reinforcement learning in average reward Markov decision processes, Knows what it knows: a framework for self-aware learning, Reducing reinforcement learning to KWIK online regression, Relational reinforcement learning with guided demonstrations, On Version Space Compression, Learning with Rejection, Learning with Deep Cascades

Uses Software

• R-MAX

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Knows what it knows: a framework for self-aware learning
• Reducing reinforcement learning to KWIK online regression
• Stochastic optimal control. The discrete time case
• The complexity of dynamic programming
• Efficient distribution-free learning of probabilistic concepts
• Toward efficient agnostic learning
• An upper bound on the loss from approximate optimal-value functions
• Selective sampling using the query by committee algorithm
• An empirical study of two approaches to sequence learning for anomaly detection
• Queries revisited.
• A sparse sampling algorithm for near-optimal planning in large Markov decision processes
• Near-optimal reinforcement learning in polynomial time
• Apple tasting.
• Generalization bounds for averaged classifiers
• Queries and concept learning
• 10.1162/153244303765208377
• Minimizing Regret With Label Efficient Prediction
• A theory of the learnable
• 10.1162/153244303321897663
• Probability Inequalities for Sums of Bounded Random Variables