On terminating Markov decision processes with a risk-averse objective function

DOI10.1016/S0005-1098(01)00084-XzbMath0995.93075OpenAlexW2042459810WikidataQ126742945 ScholiaQ126742945MaRDI QIDQ5947647

Stephen D. Patek

Publication date: 17 October 2002

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0005-1098(01)00084-x

zbMATH Keywords

convergencedynamic programmingpolicy iterationrisk-sensitive finite states Markov decision processesstochastic shortest pathsterminating problemvalue iteration

Mathematics Subject Classification ID

Dynamic programming in optimal control and differential games (49L20) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40) Existence of optimal solutions to problems involving randomness (49J55)

Related Items (8)

Regular Policies in Abstract Dynamic Programming ⋮ GUBS criterion: arbitrary trade-offs between cost and probability-to-goal in stochastic planning based on expected utility theory ⋮ Risk-sensitive multiagent decision-theoretic planning based on MDP and one-switch utility functions ⋮ Convergence of value functions for finite horizon Markov decision processes with constraints ⋮ Finite horizon risk-sensitive continuous-time Markov decision processes with unbounded transition and cost rates ⋮ Efficient algorithms for risk-sensitive Markov decision processes with limited budget ⋮ Robust shortest path planning and semicontractive dynamic programming ⋮ Computational Methods for Risk-Averse Undiscounted Transient Markov Models

Cites Work

• State-space formulae for all stabilizing controllers that satisfy an \(H_{\infty}\)-norm bound and relations to risk sensitivity
• Risk-sensitive and minimax control of discrete-time, finite-state Markov decision processes
• Risk sensitive control of Markov processes in countable state space
• Multiplicative Markov Decision Chains
• Discounted MDP’s: Distribution Functions and Exponential Utility Maximization
• Risk-sensitive linear/quadratic/gaussian control
• An Analysis of Stochastic Shortest Path Problems
• Stochastic Shortest Path Games
• The equivalence between infinite-horizon optimal control of stochastic systems with exponential-of-integral performance index and stochastic differential games
• Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games
• Risk-Sensitive Markov Decision Processes
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: On terminating Markov decision processes with a risk-averse objective function