Value function based reinforcement learning in changing Markovian environments

zbMATH Open1225.68169MaRDI QIDQ3096166FDOQ3096166

Balázs Csanád Csáji, László Monostori

Publication date: 8 November 2011

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

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

zbMATH Keywords

Markov decision processesreinforcement learningchanging environmentsvalue function bounds\((\epsilon\delta )\)-MDPsstochastic iterative algorithms

Mathematics Subject Classification ID

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

Cited In (7)

• Title not available (Why is that?)
• A reinforcement learning algorithm for trading commodities
• Title not available (Why is that?)
• Towards Min Max Generalization in Reinforcement Learning
• Concurrent Q-learning: Reinforcement learning for dynamic goals and environments
• Title not available (Why is that?)
• 10.1162/153244303768966148

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)