Testing probabilistic equivalence through reinforcement learning

DOI10.1016/J.IC.2013.02.002MaRDI QIDQ383369zbMATH OpenOpenAlexFDO

Authors Josée Desharnais, François Laviolette, Sami Zhioua

Publication date 4 December 2013

Published in Information and Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ic.2013.02.002

zbMATH Keywords

verificationdistancetestingMarkov processesdivergencereinforcement learningstochastic systemsequivalence relations

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Probability in computer science (algorithm analysis, random structures, phase transitions, etc.) (68Q87) Modes of computation (nondeterministic, parallel, interactive, probabilistic, etc.) (68Q10) Specification and verification (program logics, model checking, etc.) (68Q60)

Recommendations

• Testing Probabilistic Equivalence Through Reinforcement Learning
• Real-reward testing for probabilistic processes
• Real-reward testing for probabilistic processes (extended abstract)
• Probabilistic bisimilarity as testing equivalence
• Probability matching and reinforcement learning
• Testing theories with learnable and predictive representations
• Approximating Markovian testing equivalence
• Approximate testing equivalence based on time, probability, and observed behavior

Cites work

• scientific article; zbMATH DE number 3814961 (Why is no real title available?)
• scientific article; zbMATH DE number 4039251 (Why is no real title available?)
• scientific article; zbMATH DE number 3744561 (Why is no real title available?)
• scientific article; zbMATH DE number 107482 (Why is no real title available?)
• scientific article; zbMATH DE number 3511563 (Why is no real title available?)
• scientific article; zbMATH DE number 1231682 (Why is no real title available?)
• scientific article; zbMATH DE number 2086650 (Why is no real title available?)
• scientific article; zbMATH DE number 1418458 (Why is no real title available?)
• scientific article; zbMATH DE number 3107192 (Why is no real title available?)
• A calculus of communicating systems
• A sparse sampling algorithm for near-optimal planning in large Markov decision processes
• A testing scenario for probabilistic processes
• Algebraic laws for nondeterminism and concurrency
• An Introduction to the Application of the Theory of Probabilistic Functions of a Markov Process to Automatic Speech Recognition
• Bisimulation for labelled Markov processes
• Bisimulation for probabilistic transition systems: A coalgebraic approach
• Bisimulation through probabilistic testing
• Metrics for labelled Markov processes
• Observation equivalence as a testing equivalence
• On Choosing and Bounding Probability Metrics
• Planning and acting in partially observable stochastic domains
• Play to Test
• Probabilistic communicating processes
• Probability Inequalities for Sums of Bounded Random Variables
• Reactive, generative, and stratified models of probabilistic processes
• Refinement-oriented probability for CSP
• Testing Probabilistic Equivalence Through Reinforcement Learning
• Testing preorders for probabilistic processes.
• \({\mathcal Q}\)-learning

Cited in

(2)

• One-trial correction of legacy AI systems and stochastic separation theorems
• Testing Probabilistic Equivalence Through Reinforcement Learning

This page was built for publication: Testing probabilistic equivalence through reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q383369)