Non-Discounted Denumerable Markovian Decision Models
From MaRDI portal
Publication:5540144
DOI10.1214/aoms/1177698405zbMath0157.50504OpenAlexW2083661550MaRDI QIDQ5540144
Publication date: 1968
Published in: The Annals of Mathematical Statistics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1214/aoms/1177698405
Related Items
A new condition for the existence of optimal stationary policies in average cost Markov decision processes, A finite step algorithm via a bimatrix game to a single controller non- zero sum stochastic game, Average Cost Markov Decision Processes with Weakly Continuous Transition Probabilities, Strong 0-discount optimal policies in a Markov decision process with a Borel state space, Reduction of total-cost and average-cost MDPs with weakly continuous transition probabilities to discounted mdps, On optimality criteria for dynamic programs with long finite horizons, Invariant problems in dynamic programming - average reward criterion, Strong polynomiality of policy iterations for average-cost MDPs modeling replacement and maintenance problems, Denumerable semi-Markov decision chains with small interest rates, What do discounted optima converge to!: A theory of discount rate asymptotics in economic models, A note on the vanishing interest rate approach in average Markov decision chains with continuous and bounded costs, Discounted and average Markov decision processes with unbounded rewards: New conditions, A survey of maintenance models: The control and surveillance of deteriorating systems, An application of Markov potential theory to Markovian decision processes, Continuous time control of Markov processes on an arbitrary state space: average return criterion, Solving stochastic dynamic programming problems by linear programming — An annotated bibliography, Finite-state approximations to denumerable-state dynamic programs, Optimal control of stationary Markov processes, On the reduction of total‐cost and average‐cost MDPs to discounted MDPs, Denumerable state nonhomogeneous Markov decision processes, Undiscounted approximations of discounted regenerative models
