Risk-Sensitive Control of Discrete-Time Markov Processes with Infinite Horizon

DOI10.1137/S0363012997320614zbMath0946.93043OpenAlexW2037197628MaRDI QIDQ4943712

Łukasz Stettner, Giovanni B. Di Masi

Publication date: 19 March 2000

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

Full work available at URL: https://doi.org/10.1137/s0363012997320614

zbMATH Keywords

Bellman equationergodic controlcontrolled discrete-time Markov processesinfinite horizon risk sensitive controlexponential ergodic performance criterion

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Discrete-time control/observation systems (93C55) Optimal stochastic control (93E20)

Related Items (72)

Continuous-time zero-sum games for markov decision processes with discounted risk-sensitive cost criterion on a general state space ⋮ Risk-Sensitive Average Optimality for Discrete-Time Markov Decision Processes ⋮ Risk measurement and risk-averse control of partially observable discrete-time Markov systems ⋮ Long run risk sensitive portfolio with general factors ⋮ Unnamed Item ⋮ Controlled semi-Markov chains with risk-sensitive average cost criterion ⋮ A note on risk-sensitive control of invariant models ⋮ Zero-Sum Risk-Sensitive Stochastic Differential Games ⋮ Local Poisson equations associated with discrete-time Markov control processes ⋮ Discounted approximations to the risk-sensitive average cost in finite Markov chains ⋮ Nonzero-sum risk-sensitive continuous-time stochastic games with ergodic costs ⋮ On risk-sensitive piecewise deterministic Markov decision processes ⋮ Contractive approximations in average Markov decision chains driven by a risk-seeking controller ⋮ On the global convergence of relative value iteration for infinite-horizon risk-sensitive control of diffusions ⋮ Discounted approximations in risk-sensitive average Markov cost chains with finite state space ⋮ Certainty equivalent control of discrete time Markov processes with the average reward functional ⋮ Average criteria in denumerable semi-Markov decision chains under risk-aversion ⋮ Unnamed Item ⋮ Markov decision processes under risk sensitivity: a discount vanishing approach ⋮ Duality between large deviation control and risk-sensitive control for Markov decision processes ⋮ Linear variance bounds for particle approximations of time-homogeneous Feynman-Kac formulae ⋮ Risk-sensitivity vanishing limit for controlled Markov processes ⋮ Discrete-time zero-sum games for Markov chains with risk-sensitive average cost criterion ⋮ Characterization of the optimal average cost in Markov decision chains driven by a risk-seeking controller ⋮ An eigenvalue approach to the risk sensitive control problem in near monotone case ⋮ Zero-sum risk-sensitive stochastic games on a countable state space ⋮ Continuous-time Markov decision processes under the risk-sensitive first passage discounted cost criterion ⋮ The Vanishing Discount Approach in a class of Zero-Sum Finite Games with Risk-Sensitive Average Criterion ⋮ Risk sensitive control of diffusions with small running cost ⋮ Long-Run Risk-Sensitive Impulse Control ⋮ Average optimality for risk-sensitive control with general state space ⋮ Optimal halting policies in Markov population decision chains with constant risk posture ⋮ Time-inconsistent risk-sensitive equilibrium for countable-stated Markov decision processes ⋮ Discrete time risk sensitive control problem ⋮ Infinite horizon risk-sensitive control of diffusions without any blanket stability assumptions ⋮ A Poisson equation for the risk-sensitive average cost in semi-Markov chains ⋮ A characterization of the optimal risk-sensitive average cost in finite controlled Markov chains ⋮ A discounted approach in communicating average Markov decision chains under risk-aversion ⋮ A risk-sensitive control dual approach to a large deviations control problem ⋮ Risk-sensitive average equilibria for discrete-time stochastic games ⋮ A sensitivity formula for risk-sensitive cost and the actor-critic algorithm ⋮ Risk-sensitive dividend problems ⋮ Zero-sum risk-sensitive stochastic games ⋮ Markov decision processes with risk-sensitive criteria: an overview ⋮ Risk-sensitive discounted Markov decision processes with unbounded reward functions and Borel spaces ⋮ Existence of bounded solutions to multiplicative Poisson equations under mixing property ⋮ A discount vanishing approximation for Markov decision processes with risk sensitivity ⋮ Risk-sensitive average Markov decision processes in general spaces ⋮ Denumerable Markov stopping games with risk-sensitive total reward criterion. ⋮ Unnamed Item ⋮ Long-run risk sensitive dyadic impulse control ⋮ Entropic risk for turn-based stochastic games ⋮ Blackwell optimality and policy stability for long-run risk-sensitive stochastic control ⋮ Risk-sensitive control of continuous time Markov chains ⋮ Vanishing discount approximations in controlled Markov chains with risk-sensitive average criterion ⋮ Necessary and sufficient conditions for a solution to the risk-sensitive Poisson equation on a finite state space ⋮ Nonzero-Sum Risk-Sensitive Stochastic Games on a Countable State Space ⋮ Characterization of the Optimal Risk-Sensitive Average Cost in Denumerable Markov Decision Chains ⋮ Nonstationary value iteration in controlled Markov chains with risk-sensitive average criterion ⋮ Risk-sensitive zero-sum stochastic differential game for jump-diffusions ⋮ On the relative value iteration with a risk-sensitive criterion ⋮ Markov decision processes under ambiguity ⋮ Contractive approximations in risk-sensitive average semi-Markov decision chains on a finite state space ⋮ Infinite horizon risk sensitive control of discrete time Markov processes with small risk ⋮ Risk-averse autonomous systems: a brief history and recent developments from the perspective of optimal control ⋮ Constant risk aversion in stochastic contests with exponential completion times ⋮ Invariant measures for multidimensional fractional stochastic volatility models ⋮ A Convex Analytic Approach to Risk-Aware Markov Decision Processes ⋮ Ergodic risk-sensitive control of Markov processes on countable state space revisited ⋮ Computational Methods for Risk-Averse Undiscounted Transient Markov Models ⋮ Continuity of the optimal average cost in Markov decision chains with small risk-sensitivity ⋮ Process-based risk measures and risk-averse control of discrete-time systems

This page was built for publication: Risk-Sensitive Control of Discrete-Time Markov Processes with Infinite Horizon