Probabilistically distorted risk-sensitive infinite-horizon dynamic programming

DOI10.1016/J.AUTOMATICA.2018.07.028MaRDI QIDQ1716491zbMATH OpenOpenAlexWikidataFDO

Authors Kun Lin, Cheng Jie, Steven I. Marcus

Publication date 5 February 2019

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.automatica.2018.07.028

zbMATH Keywords

dynamic programmingrisk measurescumulative prospect theory

Mathematics Subject Classification ID

Decision theory (91B06) Dynamic programming (90C39) Utility theory (91B16)

Recommendations

• More risk-sensitive Markov decision processes
• Risk-sensitive reinforcement learning
• Risk-sensitive Markov control processes
• Risk-averse dynamic programming for Markov decision processes
• Nearly optimal policies in risk-sensitive positive dynamic programming on discrete spaces.

Cites work

• scientific article; zbMATH DE number 1795842 (Why is no real title available?)
• Abstract dynamic programming
• Advances in prospect theory: cumulative representation of uncertainty
• Coherent and convex monetary risk measures for bounded càdlàg processes
• Coherent measures of risk
• Conditional Risk Mappings
• Dynamic coherent risk measures
• On the Theory of Dynamic Programming
• Portfolio choice via quantiles
• Prospect Theory: An Analysis of Decision under Risk
• Prospect theory. For risk and ambiguity.
• Risk-averse control of undiscounted transient Markov models
• Risk-averse dynamic programming for Markov decision processes

Cited in

(5)

• Nearly optimal policies in risk-sensitive positive dynamic programming on discrete spaces.
• Dynamic programming with value convexity
• Risk-Sensitive Reinforcement Learning via Policy Gradient Search
• Preference robust state-dependent distortion risk measure on act space and its application in optimal decision making
• Distorted probability operator for dynamic portfolio optimization in times of socio-economic crisis

This page was built for publication: Probabilistically distorted risk-sensitive infinite-horizon dynamic programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1716491)