The Value Iteration Algorithm in Risk-Sensitive Average Markov Decision Chains with Finite State Space

DOI10.1287/MOOR.28.4.752.20515zbMath1082.90125OpenAlexW2070443156MaRDI QIDQ5704149

Rolando Cavazos-Cadena, Raúl Montes-De-oca

Publication date: 11 November 2005

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

Full work available at URL: https://doi.org/10.1287/moor.28.4.752.20515

zbMATH Keywords

Schweitzer's transformationSuccessive approximations methodrisk-sensitive average optimality equationstopping rule for the value iteration scheme

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Related Items (7)

Unnamed Item ⋮ On the global convergence of relative value iteration for infinite-horizon risk-sensitive control of diffusions ⋮ Optimal halting policies in Markov population decision chains with constant risk posture ⋮ Risk-sensitive reinforcement learning algorithms with generalized average criterion ⋮ Nonstationary value iteration in controlled Markov chains with risk-sensitive average criterion ⋮ On the relative value iteration with a risk-sensitive criterion ⋮ Constant risk aversion in stochastic contests with exponential completion times

This page was built for publication: The Value Iteration Algorithm in Risk-Sensitive Average Markov Decision Chains with Finite State Space