Mixed risk-neutral/minimax control of discrete-time, finite-state Markov decision processes

DOI10.1109/9.847737zbMath0978.93084OpenAlexW2108888882MaRDI QIDQ4507087

Steven I. Marcus, Stefano P. Coraluppi

Publication date: 17 October 2000

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/5547c401117dc851c9153c550d52e8dfca54d72c

zbMATH Keywords

optimal controldynamic programming equationfinite state Markov decision processesrisk-neutral/minimax control

Mathematics Subject Classification ID

Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Related Items (8)

Risk-Sensitive Reinforcement Learning via Policy Gradient Search ⋮ Control systems of interacting objects modeled as a game against nature under a mean field approach ⋮ Non-randomized policies for constrained Markov decision processes ⋮ Semi-Markov control models with partially known holding times distribution: discounted and average criteria ⋮ Discounted robust control for Markov diffusion processes ⋮ Minimax control for discrete-time time-varying stochastic systems ⋮ On the use of stochastic differential games against nature to ergodic control problems with unknown parameters ⋮ Computational Methods for Risk-Averse Undiscounted Transient Markov Models

This page was built for publication: Mixed risk-neutral/minimax control of discrete-time, finite-state Markov decision processes