Duality between large deviation control and risk-sensitive control for Markov decision processes

DOI10.1016/j.sysconle.2023.105490zbMath1522.90247OpenAlexW4323430107MaRDI QIDQ6161353

Jinwen Chen, Yanan Dai

Publication date: 27 June 2023

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.sysconle.2023.105490

zbMATH Keywords

dualitylarge deviationMarkov decision processrisk-sensitive control

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (1)

Markov decision processes under risk sensitivity: a discount vanishing approach

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Downside risk minimization via a large deviations approach
• Large deviations techniques and applications.
• A large deviations approach to optimal long term investment
• Infinite horizon risk sensitive control of discrete time Markov processes with small risk
• Asymptotics of the probability minimizing a ``down-side risk
• On long term investment optimality
• Average optimality for risk-sensitive control with general state space
• A risk-sensitive control dual approach to a large deviations control problem
• ON PORTFOLIO CHOICE BY MAXIMIZING THE OUTPERFORMANCE PROBABILITY
• Risk-Sensitive Control of Finite State Machines on an Infinite Horizon I
• Risk-Sensitive Control of Discrete-Time Markov Processes with Infinite Horizon
• On the policy improvement algorithm for ergodic risk-sensitive control
• A Variational Formula for Risk-Sensitive Reward
• A Variational Characterization of the Risk-Sensitive Average Reward for Controlled Diffusions on $\mathbb{R}^d$

This page was built for publication: Duality between large deviation control and risk-sensitive control for Markov decision processes