On Finding Optimal Policies in Discrete Dynamic Programming with No Discounting
From MaRDI portal
Publication:5528345
DOI10.1214/aoms/1177699272zbMath0149.16301OpenAlexW2142032013WikidataQ114846481 ScholiaQ114846481MaRDI QIDQ5528345
Publication date: 1966
Published in: The Annals of Mathematical Statistics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1214/aoms/1177699272
Related Items (46)
Index-based policies for discounted multi-armed bandits on parallel machines. ⋮ OPTIMALITY OF TRUNK RESERVATION FOR AN M/M/K/N QUEUE WITH SEVERAL CUSTOMER TYPES AND HOLDING COSTS ⋮ On the existence of relative values for undiscounted Markovian decision processes with a scalar gain rate ⋮ Bias optimality and strong \(n\) \((n= -1,0)\) discount optimality for Markov decision processes ⋮ Optimality equations and sensitive optimality in bounded Markov decision processes1 ⋮ A Mixed Value and Policy Iteration Method for Stochastic Control with Universally Measurable Policies ⋮ Strong 1-optimal stationary policies in denumerable Markov decision processes ⋮ Blackwell optimal policies in a Markov decision process with a Borel state space ⋮ A new algorithm for a multi-item periodic review inventory system ⋮ Turnpike theorems for Markov games ⋮ Generalized Markovian decision processes ⋮ Survey of linear programming for standard and nonstandard Markovian control problems. Part I: Theory ⋮ Symblicit algorithms for mean-payoff and shortest path in monotonic Markov decision processes ⋮ Strong 0-discount optimal policies in a Markov decision process with a Borel state space ⋮ A value-iteration scheme for undiscounted multichain Markov renewal programs ⋮ Strong \(n\)-discount and finite-horizon optimality for continuous-time Markov decision processes ⋮ On optimality criteria for dynamic programs with long finite horizons ⋮ An axiomatic approach to Markov decision processes ⋮ A value iteration method for undiscounted multichain Markov decision processes ⋮ Unnamed Item ⋮ Another Set of Conditions for Strongn(n = −1, 0) Discount Optimality in Markov Decision Processes ⋮ Policy improvement for perfect information additive reward and additive transition stochastic games with discounted and average payoffs ⋮ Sample-path optimality and variance-maximization for Markov decision processes ⋮ Review of a Markov decision algorithm for optimal inspections and revisions in a maintenance system with partial information ⋮ Planning for the long run: programming with patient, Pareto responsive preferences ⋮ Solution procedures for multi-objective markov decision processes ⋮ A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases ⋮ On the existence of relative values for undiscounted multichain Markov decision processes ⋮ The vanishing discount approach to constrained continuous-time controlled Markov chains ⋮ An optimality principle for Markovian decision processes ⋮ Singularly perturbed linear programs and Markov decision processes ⋮ A survey of recent results on continuous-time Markov decision processes (with comments and rejoinder) ⋮ Unnamed Item ⋮ Finite state continuous time Markov decision processes with an infinite planning horizon ⋮ Linear programming considerations on Markovian decision processes with no discounting ⋮ On direct sums of Markovian decision process ⋮ On the set of optimal policies in discrete dynamic programming ⋮ On a set of optimal policies in continuous time Markovian decision problem ⋮ A new optimality criterion for discrete dynamic programming ⋮ Bias optimality for multichain continuous-time Markov decision processes ⋮ Finite state multi-armed bandit problems: Sensitive-discount, average-reward and average-overtaking optimality ⋮ Maximum-Stopping-Value Policies in Finite Markov Population Decision Chains ⋮ Unnamed Item ⋮ MARKOV DECISION PROCESSES ⋮ The variational calculus and approximation in policy space for Markovian decision processes ⋮ Decentralized evolutionary mechanisms for intertemporal economies: A possibility result
This page was built for publication: On Finding Optimal Policies in Discrete Dynamic Programming with No Discounting
