Convergence of probability measures and Markov decision models with incomplete information

DOI10.1134/S0081543814080069zbMath1327.60019arXiv1407.1029MaRDI QIDQ492169

Eugene A. Feinberg, Michael Z. Zgurovsky, Pavlo O. Kasyanov

Publication date: 20 August 2015

Published in: Proceedings of the Steklov Institute of Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1407.1029

zbMATH Keywords

weak convergence of probability measures; continuity of stochastic kernels; control of stochastic systems with incomplete state observations

Mathematics Subject Classification ID

91B06: Decision theory

90C40: Markov and semi-Markov decision processes

60B10: Convergence of probability measures

Related Items

Sufficiency of Deterministic Policies for Atomless Discounted and Uniformly Absorbing MDPs with Multiple Criteria, Distribution of Values of Cantor Type Fractal Functions with Specified Restrictions, Markov Decision Processes with Incomplete Information and Semiuniform Feller Transition Probabilities, Fatou's Lemma in Its Classical Form and Lebesgue's Convergence Theorems for Varying Measures with Applications to Markov Decision Processes, Average Cost Markov Decision Processes with Semi-Uniform Feller Transition Probabilities, Solutions for zero‐sum two‐player games with noncompact decision sets and unbounded payoffs, Semi-uniform Feller stochastic kernels, Equivalent conditions for weak continuity of nonlinear filters, Uniform Fatou's lemma, On a new class of continuous indices of inequality, Weak Feller property of non-linear filters, Several different types of convergence for ND random variables under sublinear expectations, Partially Observable Total-Cost Markov Decision Processes with Weakly Continuous Transition Probabilities

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Monte Carlo model for determination of binary diffusion coefficients in gases
• Markov decision processes with applications to finance.
• Berge's theorem for noncompact image sets
• Stochastic optimal control. The discrete time case
• Incomplete information in Markovian decision models
• Optimal control of discrete time stochastic systems
• Adaptive Markov control processes
• Berge's maximum theorem for noncompact image sets
• Optimal control of partially observable Markovian systems
• Partially Observable Total-Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
• Average Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
• Optimality Conditions for Partially Observable Markov Decision Processes
• Some limit theorems for simple point processes (a martingale approach)
• Bayesian dynamic programming
• Reduction of a Controlled Markov Model with Incomplete Data to a Problem with Complete Information in the Case of Borel State and Control Space
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
• The Optimal Control of Partially Observable Markov Processes over a Finite Horizon
• Measure Theory
• Discrete-Time Markovian Decision Processes with Incomplete State Observation