Value function based reinforcement learning in changing Markovian environments

MaRDI QIDQ3096166zbMATH OpenFDO

Authors Balázs Csanád Csáji, László Monostori

Publication date 8 November 2011

Full work available at URL http://www.jmlr.org/papers/v9/csaji08a.html

zbMATH Keywords

\((\epsilon\delta )\)-MDPschanging environmentsMarkov decision processesreinforcement learningstochastic iterative algorithmsvalue function bounds

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40)

Recommendations

• 10.1162/153244303768966148
• Basis function adaptation in temporal difference reinforcement learning
• Empirical Q-value iteration
• \({\mathcal Q}\)-learning
• Markov decision processes with arbitrary reward processes

Cited in

(7)

• Towards min max generalization in reinforcement learning
• 10.1162/153244303768966148
• scientific article; zbMATH DE number 5957492 (Why is no real title available?)
• scientific article; zbMATH DE number 5525811 (Why is no real title available?)
• Learning and planning for time-varying MDPs using maximum likelihood estimation
• Concurrent Q-learning: Reinforcement learning for dynamic goals and environments
• A reinforcement learning algorithm for trading commodities

This page was built for publication: Value function based reinforcement learning in changing Markovian environments

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3096166)