An information-theoretic analysis of return maximization in reinforcement learning

DOI10.1016/J.NEUNET.2011.05.002MaRDI QIDQ2375396zbMATH OpenOpenAlexWikidataFDO

Authors Kazunori Iwata

Publication date 14 June 2013

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2011.05.002

zbMATH Keywords

information theoryreinforcement learningasymptotic equipartition propertystochastic sequential decision process

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• The asymptotic equipartition property in reinforcement learning and its relation to return maximization
• An information-theoretic analysis of Thompson sampling
• Reinforcement learning in finite MDPs: PAC analysis
• Near-optimal reinforcement learning in polynomial time
• Using Expectation-Maximization for Reinforcement Learning

Cites work

• scientific article; zbMATH DE number 3126094 (Why is no real title available?)
• scientific article; zbMATH DE number 3148886 (Why is no real title available?)
• scientific article; zbMATH DE number 3908323 (Why is no real title available?)
• scientific article; zbMATH DE number 1043533 (Why is no real title available?)
• scientific article; zbMATH DE number 1179314 (Why is no real title available?)
• scientific article; zbMATH DE number 1821199 (Why is no real title available?)
• A Mathematical Theory of Communication
• A New Optimality Criterion for Nonhomogeneous Markov Decision Processes
• A simple proof of the Moy-Perez generalization of the Shannon-McMillan theorem
• Approximation theory of output statistics
• Asymptotically mean stationary measures
• Asynchronous stochastic approximation and Q-learning
• Boundedness of iterates in \(Q\)-learning
• Convergence results for single-step on-policy reinforcement-learning algorithms
• Correction Notes: Correction to "The Individual Ergodic Theorem of Information Theory"
• Discrete Dynamic Programming
• Elements of Information Theory
• Generalizations of Shannon-McMillan theorem
• Model-Based Reinforcement Learning for Partially Observable Games with Sampling-Based State Estimation
• The Basic Theorems of Information Theory
• The Individual Ergodic Theorem of Information Theory
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• The asymptotic equipartition property in reinforcement learning and its relation to return maximization
• The convergence of \(TD(\lambda)\) for general \(\lambda\)
• The method of types [information theory]
• The role of the asymptotic equipartition property in noiseless source coding
• The strong ergodic theorem for densities: Generalized Shannon-McMillan- Breiman theorem
• \({\mathcal Q}\)-learning

Cited in

(3)

• The asymptotic equipartition property in reinforcement learning and its relation to return maximization
• An information-theoretic analysis of Thompson sampling
• Trading utility and uncertainty: applying the value of information to resolve the exploration-exploitation dilemma in reinforcement learning

This page was built for publication: An information-theoretic analysis of return maximization in reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2375396)