Risk-Averse Control of Undiscounted Transient Markov Models

DOI10.1137/13093902XzbMath1311.93087arXiv1203.5437OpenAlexW1979085877MaRDI QIDQ5244645

Ruszczyński, Andrzej, Özlem Çavuş

Publication date: 27 March 2015

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

Full work available at URL: https://arxiv.org/abs/1203.5437

zbMATH Keywords

optimal stoppingstochastic optimal controldynamic risk measuresstochastic shortest pathMarkov risk measuresdynamic programming equationsrandomized policytransient Markov modelsmultikernels

Mathematics Subject Classification ID

Dynamic programming in optimal control and differential games (49L20) Optimal stochastic control (93E20) Stopping times; optimal stopping problems; gambling theory (60G40) Markov and semi-Markov decision processes (90C40) Existence of optimal solutions to problems involving randomness (49J55)

Related Items (13)

Risk measurement and risk-averse control of partially observable discrete-time Markov systems ⋮ Optimal Control of Conditional Value-at-Risk in Continuous Time ⋮ Regular Policies in Abstract Dynamic Programming ⋮ Risk-Sensitive Reinforcement Learning via Policy Gradient Search ⋮ Index policy for multiarmed bandit problem with dynamic risk measures ⋮ Risk-Averse Stochastic Programming: Time Consistency and Optimal Stopping ⋮ Unnamed Item ⋮ Markov risk mappings and risk-sensitive optimal prediction ⋮ Probabilistically distorted risk-sensitive infinite-horizon dynamic programming ⋮ Robust optimal control using conditional risk mappings in infinite horizon ⋮ Robust Control of Partially Observable Failing Systems ⋮ Computational Methods for Risk-Averse Undiscounted Transient Markov Models ⋮ Process-based risk measures and risk-averse control of discrete-time systems

This page was built for publication: Risk-Averse Control of Undiscounted Transient Markov Models