Reducing reinforcement learning to KWIK online regression

DOI10.1007/s10472-010-9201-2zbMath1207.68243OpenAlexW2020753891MaRDI QIDQ616761

Michael L. Littman, Lihong Li

Publication date: 12 January 2011

Published in: Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10472-010-9201-2

zbMATH Keywords

reinforcement learningvalue function approximationexplorationknows what it knows (KWIK)online regressionPAC-MDP

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Solving average cost Markov decision processes by means of a two-phase time aggregation algorithm ⋮ Unnamed Item ⋮ Knows what it knows: a framework for self-aware learning ⋮ Abstraction from demonstration for efficient reinforcement learning in high-dimensional domains

Uses Software

• R-MAX

Cites Work

• Knows what it knows: a framework for self-aware learning
• The complexity of dynamic programming
• A sparse sampling algorithm for near-optimal planning in large Markov decision processes
• Near-optimal reinforcement learning in polynomial time
• The effect of representation and knowledge on goal-directed exploration with reinforcement-learning algorithms
• 10.1162/153244303765208377
• 10.1162/153244303321897663
• 10.1162/1532443041827907
• Prediction, Learning, and Games
• A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Reducing reinforcement learning to KWIK online regression