Comparing Policies in Markov Decision Processes: Mandl's Lemma Revisited

DOI10.1287/MOOR.15.1.155zbMATH Open0714.90097OpenAlexW2054860096WikidataQ124881108 ScholiaQ124881108MaRDI QIDQ3200907FDOQ3200907

Authors: Adam Shwartz, Armand M. Makowski 

Publication date: 1990

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

Full work available at URL: https://doi.org/10.1287/moor.15.1.155

Recommendations

• scientific article; zbMATH DE number 970511
• Adaptive control of discounted Markov decision chains
• Optimal Adaptive Policies for Markov Decision Processes
• Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded Costs
• Value iteration and approximately optimal stationary policies in finite-state average Markov decision chains

zbMATH Keywords

convergence conditionsPolish state spaceaverage costsMarkov decision chain

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47) Markov and semi-Markov decision processes (90C40) Adaptive control/observation systems (93C40)

Cited In (3)

• On ordinal comparison of policies in Markov reward processes
• Stochastic approximations for finite-state Markov chains
• Stability and probability. I: Convergence for queueing networks via Lyapunov optimization

This page was built for publication: Comparing Policies in Markov Decision Processes: Mandl's Lemma Revisited

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3200907)