Efficient PAC learning for episodic tasks with acyclic state spaces

DOI10.1007/S10626-007-0014-3MaRDI QIDQ2465672zbMATH OpenOpenAlexFDO

Authors Theologos Bountourelis, Spyros Reveliotis

Publication date 7 January 2008

Published in Discrete Event Dynamic Systems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10626-007-0014-3

zbMATH Keywords

Computational learning theoryEfficient probably approximately correct (PAC) algorithmsMachine learningMarkov decision processesRanking \& selectionUncertainty management

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40) Control/observation systems with incomplete information (93C41) Discrete event control/observation systems (93C65)

Recommendations

• scientific article; zbMATH DE number 2089367
• Reinforcement learning in finite MDPs: PAC analysis
• Markov decision processes with arbitrary reward processes
• Simulation-based optimization of Markov decision processes: an empirical process theory approach
• PAC Bounds for Discounted MDPs

Cites work

• A Single-Sample Multiple Decision Procedure for Ranking Means of Normal Populations with known Variances
• Efficient PAC learning for episodic tasks with acyclic state spaces
• scientific article; zbMATH DE number 2089367 (Why is no real title available?)
• scientific article; zbMATH DE number 1179314 (Why is no real title available?)
• scientific article; zbMATH DE number 3349081 (Why is no real title available?)
• scientific article; zbMATH DE number 2238781 (Why is no real title available?)
• Near-optimal reinforcement learning in polynomial time
• Probability Inequalities for Sums of Bounded Random Variables

Cited in

(3)

• Efficient PAC learning for episodic tasks with acyclic state spaces
• Optimal flow control in acyclic networks with uncontrollable routings and precedence constraints
• Optimal node visitation in acyclic stochastic digraphs with multi-threaded traversals and internal visitation requirements

This page was built for publication: Efficient PAC learning for episodic tasks with acyclic state spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2465672)