Minimizing risk models in Markov decision processes with policies depending on target values

DOI10.1006/jmaa.1998.6203zbMath0917.90285OpenAlexW1987073631MaRDI QIDQ1282996

Yuanlie Lin, Congbin Wu

Publication date: 19 July 1999

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jmaa.1998.6203

zbMATH Keywords

infinite horizonMarkov decision processesoptimality equationcountable state spaceexistence of optimal policyminimizing risk problems

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (28)

Value iteration methods in risk minimizing stopping problems ⋮ Discrete time credibilistic processes: construction and convergences ⋮ Analyzing operational risk-reward trade-offs for start-ups ⋮ Zero-sum semi-Markov games with a probability criterion ⋮ The risk probability criterion for discounted continuous-time Markov decision processes ⋮ Markov decision processes with average-value-at-risk criteria ⋮ Stochastic shortest path problems with associative accumulative criteria ⋮ Finite horizon semi-Markov decision processes with application to maintenance systems ⋮ Threshold probability of non-terminal type in finite horizon Markov decision processes ⋮ Optimal threshold probability in undiscounted Markov decision processes with a target set. ⋮ Percentile queries in multi-dimensional Markov decision processes ⋮ Risk-Constrained Reinforcement Learning with Percentile Risk Criteria ⋮ Meet your expectations with guarantees: beyond worst-case synthesis in quantitative games ⋮ Variance-penalized Markov decision processes: dynamic programming and reinforcement learning techniques ⋮ Markov decision processes associated with two threshold probability criteria ⋮ Optimal risk probability for first passage models in semi-Markov decision processes ⋮ Optimal threshold probability and expectation in semi-Markov decision processes ⋮ Arriving on time ⋮ Markov decision processes with a target set for minimum criteria ⋮ Time consistent dynamic risk measures ⋮ Continuous-time zero-sum games with probability criterion ⋮ First passage risk probability optimality for continuous time Markov decision processes ⋮ Stochastic optimization of forward recursive functions ⋮ Nonzero-sum stochastic games with probability criteria ⋮ STOCHASTIC SEQUENTIAL ASSIGNMENT PROBLEM WITH THRESHOLD CRITERIA ⋮ Optimal policy for minimizing risk models in Markov decision processes ⋮ Optimal decisions in stochastic graphs with uncorrelated and correlated edge weights ⋮ Computational Methods for Risk-Averse Undiscounted Transient Markov Models

Cites Work

• Adaptive Markov control processes
• Mean, variance and probabilistic criteria in finite Markov decision processes: A review
• Target-level criterion in Markov decision processes
• Minimising a threshold probability in discounted Markov decision processes
• Discounted MDP’s: Distribution Functions and Exponential Utility Maximization
• The variance of discounted Markov decision processes
• Percentile performance criteria for limiting average Markov decision processes

This page was built for publication: Minimizing risk models in Markov decision processes with policies depending on target values