4.6 Article

RISK-SENSITIVE AVERAGE OPTIMALITY FOR DISCRETE-TIME MARKOV DECISION PROCESSES

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Automation & Control Systems

Ergodic risk-sensitive control of Markov processes on countable state space revisited

Anup Biswas et al.

Summary: We consider a large family of discrete and continuous time controlled Markov processes and study an ergodic risk-sensitive minimization problem. Under a blanket stability assumption, we provide a complete analysis to this problem, including the uniqueness of the value function and verification result for optimal stationary Markov controls, along with the existence results. We also revisit this problem under a near-monotonicity condition, without any stability hypothesis, and propose policy improvement algorithms in both discrete and continuous time frameworks.

ESAIM-CONTROL OPTIMISATION AND CALCULUS OF VARIATIONS (2022)

Article Mathematics, Applied

On the policy improvement algorithm for ergodic risk-sensitive control

Ari Arapostathis et al.

Summary: This article discusses the ergodic risk-sensitive control problem for a class of multidimensional controlled diffusions on the entire space. The study includes minimization and maximization problems under different stability assumptions and a near-monotone assumption on the running cost. It establishes the convergence of the policy improvement algorithm for these models and presents a more general result on the equilibrium's region of attraction.

PROCEEDINGS OF THE ROYAL SOCIETY OF EDINBURGH SECTION A-MATHEMATICS (2021)

Article Mathematics, Interdisciplinary Applications

Nonzero-sum Risk-Sensitive Average Stochastic Games: The Case of Unbounded Costs

Qingda Wei et al.

Summary: This paper studies discrete-time nonzero-sum stochastic games under the risk-sensitive average cost criterion. It introduces risk-sensitive first passage payoff functions and their properties, establishes the existence of a solution to the risk-sensitive average cost optimality equation for the case of unbounded cost functions, and demonstrates the existence of a randomized stationary Nash equilibrium in the class of randomized history-dependent strategies. The main results are illustrated using a controlled population system.

DYNAMIC GAMES AND APPLICATIONS (2021)

Article Operations Research & Management Science

A Discounted Approach in Communicating Average Markov Decision Chains Under Risk-Aversion

Julio Saucedo-Zul et al.

JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS (2020)

Article Automation & Control Systems

THE VANISHING DISCOUNT APPROACH IN A CLASS OF ZERO-SUM FINITE GAMES WITH RISK-SENSITIVE AVERAGE CRITERION

Rolando Cavazos-Cadena et al.

SIAM JOURNAL ON CONTROL AND OPTIMIZATION (2019)

Article Operations Research & Management Science

Nonzero-Sum Risk-Sensitive Stochastic Games on a Countable State Space

Arnab Basu et al.

MATHEMATICS OF OPERATIONS RESEARCH (2018)

Article Operations Research & Management Science

Characterization of the Optimal Risk-Sensitive Average Cost in Denumerable Markov Decision Chains

Rolando Cavazos-Cadena

MATHEMATICS OF OPERATIONS RESEARCH (2018)

Article Automation & Control Systems

MARKOV-NASH EQUILIBRIA IN MEAN-FIELD GAMES WITH DISCOUNTED COST

Naci Saldi et al.

SIAM JOURNAL ON CONTROL AND OPTIMIZATION (2018)

Article Statistics & Probability

Zero-sum risk-sensitive stochastic games

Nicole Bauerle et al.

STOCHASTIC PROCESSES AND THEIR APPLICATIONS (2017)

Article Operations Research & Management Science

More Risk-Sensitive Markov Decision Processes

Nicole Baeuerle et al.

MATHEMATICS OF OPERATIONS RESEARCH (2014)

Article Statistics & Probability

Zero-sum risk-sensitive stochastic games on a countable state space

Arnab Basu et al.

STOCHASTIC PROCESSES AND THEIR APPLICATIONS (2014)

Article Automation & Control Systems

RISK-SENSITIVE MARKOV CONTROL PROCESSES

Yun Shen et al.

SIAM JOURNAL ON CONTROL AND OPTIMIZATION (2013)

Article Statistics & Probability

Average optimality for risk-sensitive control with general state space

Anna Jaskiewicz

ANNALS OF APPLIED PROBABILITY (2007)

Article Automation & Control Systems

Infinite horizon risk sensitive control of discrete time Markov processes under minorization property

Giovanni B. Di Masi et al.

SIAM JOURNAL ON CONTROL AND OPTIMIZATION (2007)

Article Operations Research & Management Science

Risk-sensitive optimal control for Markov decision processes with monotone cost

VS Borkar et al.

MATHEMATICS OF OPERATIONS RESEARCH (2002)

Article Statistics & Probability

Multiplicative ergodicity and large deviations for an irreducible Markov chain

S Balaji et al.

STOCHASTIC PROCESSES AND THEIR APPLICATIONS (2000)