Constrained Markov Decision Models with Weighted Discounted Rewards

DOI10.1287/moor.20.2.302zbMath0837.90120MaRDI QIDQ4848417

Adam Shwartz, Eugene A. Feinberg

Publication date: 17 September 1995

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/cf418e5ff1623104bd451bcd422937f25236d001

zbMATH Keywords

Markov decision processes; constrained optimization; discounted rewards; randomized stationary policy; approximate solutions of constrained weighted discounted models

Mathematics Subject Classification ID

90C05: Linear programming

90C40: Markov and semi-Markov decision processes

Related Items

Selecting malaria interventions: a top-down approach, Discounted continuous-time constrained Markov decision processes in Polish spaces, Markov control models with unknown random state-action-dependent discount factors, Sensitivity analysis and optimal ultimately stationary deterministic policies in some constrained discounted cost models, Transfer in variable-reward hierarchical reinforcement learning, Multiple solutions under quasi-exponential discounting, Resource-constrained management of heterogeneous assets with stochastic deterioration, Constrained Markovian decision processes: The dynamic programming approach, Average-discounted equilibria in stochastic games, Nonatomic total rewards Markov decision processes with multiple criteria, Markov-achievable payoffs for finite-horizon decision models., Time consistent Markov policies in dynamic economies with quasi-hyperbolic consumers, Constrained discounted Markov decision processes with Borel state spaces, Markov control processes with randomized discounted cost