Nonstationary denumerable state Markov decision processes -- with average variance criterion
From MaRDI portal
Publication:1299921
zbMath1016.90071MaRDI QIDQ1299921
Publication date: 7 September 1999
Published in: Mathematical Methods of Operations Research (Search for Journal in Brave)
optimal Markov policiesdiscrete-time Markov decision processesoptimality equationsaverage expected reward criterionaverage variance criterionnonstationary Markov decision processes
Markov processes: estimation; hidden Markov models (62M05) Markov and semi-Markov decision processes (90C40)
Related Items