Blackwell optimality and policy stability for long-run risk-sensitive stochastic control

DOI10.1137/24M1671335MaRDI QIDQ6652399zbMATH OpenFDO

Authors Nicole Bäuerle, Marcin Pitera, Łukasz Stettner

Publication date 12 December 2024

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/24M1671335

zbMATH Keywords

blackwell optimalityentropic utilitylong time horizonMarkov decision process (MDP)risk-sensitive stochastic controlspan-contraction approachvanishing discount

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Transition functions, generators and resolvents (60J35) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40) Discrete-time control/observation systems (93C55) Optimal stochastic control (93E20)

Recommendations

• Existence of risk-sensitive optimal stationary policies for controlled Markov processes
• Risk-Sensitive Control of Discrete-Time Markov Processes with Infinite Horizon
• Risk-sensitive and minimax control of discrete-time, finite-state Markov decision processes
• Long run stochastic control problems with general discounting
• Some results and problems in risk sensitive stochastic control

Cites work

• A CONVEXITY PROPERTY OF POSITIVE MATRICES
• A note on a new class of recursive utilities in Markov decision processes
• A Utility Criterion for Markov Decision Processes
• Average, Sensitive and Blackwell Optimal Policies in Denumerable Markov Decision Chains with Unbounded Rewards
• Certainty equivalent control of discrete time Markov processes with the average reward functional
• Continuity of the optimal average cost in Markov decision chains with small risk-sensitivity
• Contractive approximations in average Markov decision chains driven by a risk-seeking controller
• Discounted approximations for risk-sensitive average criteria in Markov decision chains with finite state space
• Discounted approximations to the risk-sensitive average cost in finite Markov chains
• Discrete Dynamic Programming
• Discrete time risk sensitive control problem
• Existence of bounded solutions to multiplicative Poisson equations under mixing property
• scientific article; zbMATH DE number 48691 (Why is no real title available?)
• scientific article; zbMATH DE number 1460605 (Why is no real title available?)
• Linear algebra and its applications
• Markov decision processes with a new optimality criterion: Discrete time
• Markov decision processes with applications to finance.
• Markov decision processes with risk-sensitive criteria: an overview
• More risk-sensitive Markov decision processes
• Necessary and sufficient conditions for a solution to the risk-sensitive Poisson equation on a finite state space
• Primitivity and Hurwitz Primitivity of Nonnegative Matrix Tuples: A Unified Approach
• Representation results for law invariant time consistent functions
• Risk-Sensitive Control of Discrete-Time Markov Processes with Infinite Horizon
• Risk-Sensitive Markov Decision Processes
• Sets of nonnegative matrices with positive inhomogeneous products
• The vanishing discount approach in Markov chains with risk-sensitive criteria
• Uniform turnpike theorems for finite Markov decision processes
• Vanishing discount approximations in controlled Markov chains with risk-sensitive average criterion

Cited in

(2)

• Ergodic risk-sensitive admission control problem for a Markovian multi-server queueing system with abandonment
• Large deviations and optimal control for Markov decision processes

This page was built for publication: Blackwell optimality and policy stability for long-run risk-sensitive stochastic control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6652399)