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

DOI10.1007/S10994-010-5225-4zbMATH Open1237.68154OpenAlexW2488247662MaRDI QIDQ413843FDOQ413843

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

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

Recommendations

• Reducing reinforcement learning to KWIK online regression
• Learning to reason
• scientific article; zbMATH DE number 1907146
• Learning to reason with a restricted view
• The knowledge gradient algorithm for a general class of online learning problems

zbMATH Keywords

reinforcement learningexplorationactive learningcomputational learning theoryknows what it knows (KWIK)mistake boundprobably approximately correct (PAC)

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32)

Cites Work

• 10.1162/153244303765208377
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Probability Inequalities for Sums of Bounded Random Variables
• A tutorial on conformal prediction
• Title not available (Why is that?)
• Stochastic optimal control. The discrete time case
• Queries and concept learning
• 10.1162/153244303321897663
• A theory of the learnable
• Toward efficient agnostic learning
• Selective sampling using the query by committee algorithm
• Title not available (Why is that?)
• Title not available (Why is that?)
• Reducing reinforcement learning to KWIK online regression
• The complexity of dynamic programming
• Reinforcement learning in finite MDPs: PAC analysis
• A sparse sampling algorithm for near-optimal planning in large Markov decision processes
• Knows what it knows: a framework for self-aware learning
• Minimizing Regret With Label Efficient Prediction
• An upper bound on the loss from approximate optimal-value functions
• Efficient distribution-free learning of probabilistic concepts
• An empirical study of two approaches to sequence learning for anomaly detection
• Queries revisited.
• Near-optimal reinforcement learning in polynomial time
• Apple tasting.
• Generalization bounds for averaged classifiers
• Provably efficient learning with typed parametric models
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (11)

• Learning with deep cascades
• Relational reinforcement learning with guided demonstrations
• On version space compression
• Consistency of plug-in confidence sets for classification in semi-supervised learning
• Reducing reinforcement learning to KWIK online regression
• Learning with Rejection
• Transferable dynamics models for efficient object-oriented reinforcement learning
• Adaptive aggregation for reinforcement learning in average reward Markov decision processes
• Knows what it knows: a framework for self-aware learning
• Relational reinforcement learning for planning with exogenous effects
• Deep exploration via randomized value functions

Uses Software

• R-MAX

This page was built for publication: Knows what it knows: a framework for self-aware learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q413843)