How Does the Value Function of a Markov Decision Process Depend on the Transition Probabilities?
From MaRDI portal
Publication:4385165
DOI10.1287/moor.22.4.872zbMath0892.90178OpenAlexW2009543467MaRDI QIDQ4385165
Publication date: 16 July 1998
Published in: Mathematics of Operations Research (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1287/moor.22.4.872
Sensitivity, stability, parametric optimization (90C31) Inventory, storage, reservoirs (90B05) Dynamic programming (90C39) Stopping times; optimal stopping problems; gambling theory (60G40) Markov and semi-Markov decision processes (90C40)
Related Items
A central limit theorem for costs in Bulinskaya's inventory management problem when deliveries face delays, Unnamed Item, A concept of copula robustness and its applications in quantitative risk management, Robustness to Incorrect System Models in Stochastic Control, Robustness and sample complexity of model-based MARL for general-sum Markov games, First-order sensitivity of the optimal value in a Markov decision model with respect to deviations in the transition probability function, Unnamed Item, An Approximate Dynamic Programming Algorithm for Monotone Value Functions, Optimal learning with non-Gaussian rewards, Effects of System Parameters on the Optimal Cost and Policy in a Class of Multidimensional Queueing Control Problems, Effects of system parameters on the optimal policy structure in a class of queueing control problems, Limiting optimal discounted-cost control of a class of time-varying stochastic systems, Stochastic Comparative Statics in Markov Decision Processes, Distributionally Robust Markov Decision Processes and Their Connection to Risk Measures, A stability result for linear Markovian stochastic optimization problems