Blackwell optimality and policy stability for long-run risk-sensitive stochastic control
DOI10.1137/24M1671335MaRDI QIDQ6652399FDOQ6652399
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)
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
risk-sensitive stochastic controlMarkov decision process (MDP)vanishing discountlong time horizonblackwell optimalityentropic utilityspan-contraction approach
Dynamic programming (90C39) Discrete-time Markov processes on general state spaces (60J05) Transition functions, generators and resolvents (60J35) Markov and semi-Markov decision processes (90C40) Discrete-time control/observation systems (93C55) Optimal stochastic control (93E20)
Cites Work
- Title not available (Why is that?)
- Linear algebra and its applications
- Representation results for law invariant time consistent functions
- Title not available (Why is that?)
- Risk-Sensitive Control of Discrete-Time Markov Processes with Infinite Horizon
- Discrete Dynamic Programming
- Markov decision processes with applications to finance.
- More risk-sensitive Markov decision processes
- Risk-Sensitive Markov Decision Processes
- A CONVEXITY PROPERTY OF POSITIVE MATRICES
- Average, Sensitive and Blackwell Optimal Policies in Denumerable Markov Decision Chains with Unbounded Rewards
- Sets of nonnegative matrices with positive inhomogeneous products
- Certainty equivalent control of discrete time Markov processes with the average reward functional
- Discounted approximations for risk-sensitive average criteria in Markov decision chains with finite state space
- Markov decision processes with a new optimality criterion: Discrete time
- A Utility Criterion for Markov Decision Processes
- A note on a new class of recursive utilities in Markov decision processes
- Necessary and sufficient conditions for a solution to the risk-sensitive Poisson equation on a finite state space
- Discounted approximations to the risk-sensitive average cost in finite Markov chains
- Continuity of the optimal average cost in Markov decision chains with small risk-sensitivity
- Vanishing discount approximations in controlled Markov chains with risk-sensitive average criterion
- The vanishing discount approach in Markov chains with risk-sensitive criteria
- Uniform turnpike theorems for finite Markov decision processes
- Primitivity and Hurwitz Primitivity of Nonnegative Matrix Tuples: A Unified Approach
- Contractive approximations in average Markov decision chains driven by a risk-seeking controller
- Markov decision processes with risk-sensitive criteria: an overview
- Existence of bounded solutions to multiplicative Poisson equations under mixing property
- Discrete time risk sensitive control problem
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)
