On the Empirical State-Action Frequencies in Markov Decision Processes Under General Policies

DOI10.1287/MOOR.1050.0148MaRDI QIDQ5704236zbMATH OpenOpenAlexFDO

Authors Shie Mannor, John N. Tsitsiklis

Publication date 11 November 2005

Published in Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL https://semanticscholar.org/paper/1c93280ca091393d0653ef1e21874f761d6b3653

zbMATH Keywords

large deviationsMarkov decision processesempirical measurestate-action frequencies

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Limit theorems in probability theory (60F99) Markov and semi-Markov decision processes (90C40)

Recommendations

• Fast convergence to state-action frequency polytopes for MDPs
• Achieving Target State-Action Frequencies in Multichain Average-Reward Markov Decision Processes
• Markov Decision Problems and State-Action Frequencies
• scientific article; zbMATH DE number 1440130
• Simulation-based optimization of Markov decision processes: an empirical process theory approach

Cited in

(6)

• Fast convergence to state-action frequency polytopes for MDPs
• Fluctuation Bounds for the Max-Weight Policy with Applications to State Space Collapse
• NP-hardness of checking the unichain condition in average cost MDPs
• Simulation-based optimization of Markov decision processes: an empirical process theory approach
• Acceptable strategy profiles in stochastic games
• Stationary anonymous sequential games with undiscounted rewards

This page was built for publication: On the Empirical State-Action Frequencies in Markov Decision Processes Under General Policies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5704236)