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

DOI10.1287/moor.1050.0148zbMath1082.90131OpenAlexW2136937392MaRDI QIDQ5704236

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

Markov decision processeslarge deviationsempirical measurestate-action frequencies

Mathematics Subject Classification ID

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

Related Items (6)

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

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