Nonstationary value iteration in controlled Markov chains with risk-sensitive average criterion

DOI10.1239/jap/1134587805zbMath1105.90101OpenAlexW1986667174MaRDI QIDQ5476137

Rolando Cavazos-Cadena, Raúl Montes-De-oca

Publication date: 29 June 2006

Published in: Journal of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1239/jap/1134587805

zbMATH Keywords

Birkhoff's contraction coefficientSchweitzer's transformationapproximate solution to the optimality equationnonstationary successive approximations algorithm

Mathematics Subject Classification ID

Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Related Items

Unnamed Item, On the global convergence of relative value iteration for infinite-horizon risk-sensitive control of diffusions, Risk-sensitive semi-Markov decision processes with general utilities and multiple criteria, On the relative value iteration with a risk-sensitive criterion

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Necessary and sufficient conditions for a bounded solution to the optimality equation in average reward Markov decision chains
• Nonstationary Markov decision problems with converging parameters
• Non-negative matrices and Markov chains. 2nd ed
• An alternative derivation of Birkhoff's formula for the contraction coefficient of a positive matrix.
• Infinite horizon risk sensitive control of discrete time Markov processes with small risk
• Adaptive Markov control processes
• Risk sensitive control of finite state Markov chains in discrete time, with applications to portfolio management
• Iterative solution of the functional equations of undiscounted Markov renewal programming
• Risk-Sensitive Control of Discrete-Time Markov Processes with Infinite Horizon
• Risk-Sensitive Optimal Control for Markov Decision Processes with Monotone Cost
• The Value Iteration Algorithm in Risk-Sensitive Average Markov Decision Chains with Finite State Space