Utility, probabilistic constraints, mean and variance of discounted rewards in Markov decision processes

DOI10.1007/BF01720793zbMath0622.90090MaRDI QIDQ1091281

Douglas J. White

Publication date: 1987

Published in: OR Spektrum (Search for Journal in Brave)

zbMATH Keywords

discounted rewards; discounted Markov decision processes; augmented state-spaces; finite state-space

Mathematics Subject Classification ID

90C40: Markov and semi-Markov decision processes

Related Items

Finding Optimal Survey Policies via Adaptive Markov Decision Processes, Non-homogeneous Markov decision processes with a constraint, Optimal policy for minimizing risk models in Markov decision processes, Value iteration methods in risk minimizing stopping problems, Expected utility maximization of optimal stopping problems, Experiments with dynamic programming algorithms for nonseparable problems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Finite state Markovian decision processes
• The Decomposition Algorithm for Linear Programs
• Controlled Markov Processes with Arbitrary Numerical Criteria
• Generalized Lagrange Multiplier Method for Solving Problems of Optimum Allocation of Resources
• Non-Randomized Markov and Semi-Markov Strategies in Dynamic Programming
• Decision Problems with Expected Utility Critera, I: Upper and Lower Convergent Utility
• The variance of discounted Markov decision processes
• Technical Note—Dynamic Programming and Probabilistic Constraints
• Discounted Dynamic Programming
• Some Remarks on Finite Horizon Markovian Decision Models