Counter examples for compact action markov decision chains with average reward criteria

DOI10.1080/15326348708807061zbMath0646.90087OpenAlexW2139024073MaRDI QIDQ3790965

Rommert Dekker

Publication date: 1987

Published in: Communications in Statistics. Stochastic Models (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/15326348708807061

zbMATH Keywords

counterexamplesaverage rewardscompact-action finite-state Markov decision chainspolicy-improvement

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (4)

Policy iteration type algorithms for recurrent state Markov decision processes ⋮ Optimization of a special case of continuous-time Markov decision processes with compact action set ⋮ Unnamed Item ⋮ Policy iteration for continuous-time average reward Markov decision processes in Polish spaces

This page was built for publication: Counter examples for compact action markov decision chains with average reward criteria