Solution to the risk-sensitive average cost optimality equation in a class of Markov decision processes with finite state space
From MaRDI portal
Publication:1395376
DOI10.1007/s001860200256zbMath1023.90076OpenAlexW2015035063MaRDI QIDQ1395376
Publication date: 26 June 2003
Published in: Mathematical Methods of Operations Research (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s001860200256
exponential utility functioncontractive operatorconstant average costconstant risk sensitivityweak communication condition
Discrete-time Markov processes on general state spaces (60J05) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)
Related Items (8)
Unnamed Item ⋮ Local Poisson equations associated with discrete-time Markov control processes ⋮ Unnamed Item ⋮ Markov decision processes under risk sensitivity: a discount vanishing approach ⋮ The discounted method and equivalence of average criteria for risk-sensitive Markov decision processes on Borel spaces ⋮ Unnamed Item ⋮ Solutions of the average cost optimality equation for finite Markov decision chains: Risk-sensitive and risk-neutral criteria ⋮ Continuity of the optimal average cost in Markov decision chains with small risk-sensitivity
This page was built for publication: Solution to the risk-sensitive average cost optimality equation in a class of Markov decision processes with finite state space