Fast convergence to state-action frequency polytopes for MDPs

DOI10.1016/j.orl.2008.12.003zbMath1159.90512OpenAlexW2012559397MaRDI QIDQ1015315

Mathieu Tracol

Publication date: 7 May 2009

Published in: Operations Research Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.orl.2008.12.003

zbMATH Keywords

Markov decision processespolytopesdeviation boundsstate-action frequencies

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (2)

Percentile queries in multi-dimensional Markov decision processes ⋮ Meet your expectations with guarantees: beyond worst-case synthesis in quantitative games

Cites Work

• Unnamed Item
• Unnamed Item
• Hoeffding's inequality for uniformly ergodic Markov chains
• Finite state Markovian decision processes
• Rate of Convergence of Empirical Measures and Costs in Controlled Markov Chains and Transient Optimality
• On the Empirical State-Action Frequencies in Markov Decision Processes Under General Policies

This page was built for publication: Fast convergence to state-action frequency polytopes for MDPs