Partially Observable Total-Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
From MaRDI portal
Publication:2806825
DOI10.1287/moor.2015.0746zbMath1338.90445arXiv1401.2168OpenAlexW2963292203MaRDI QIDQ2806825
Eugene A. Feinberg, Pavlo O. Kasyanov, Michael Z. Zgurovsky
Publication date: 19 May 2016
Published in: Mathematics of Operations Research (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1401.2168
Related Items
Risk measurement and risk-averse control of partially observable discrete-time Markov systems, STOCHASTIC SETUP-COST INVENTORY MODEL WITH BACKORDERS AND QUASICONVEX COST FUNCTIONS, Robustness to Incorrect Priors and Controlled Filter Stability in Partially Observed Stochastic Control, Markov Decision Processes with Incomplete Information and Semiuniform Feller Transition Probabilities, Partially observed discrete-time risk-sensitive mean field games, Semi-uniform Feller stochastic kernels, Equivalent conditions for weak continuity of nonlinear filters, Approximate Nash Equilibria in Partially Observed Stochastic Games with Mean-Field Interactions, Convergence theorems for varying measures under convexity conditions and applications, Robustness to Incorrect System Models in Stochastic Control, Fatou's Lemma in Its Classical Form and Lebesgue's Convergence Theorems for Varying Measures with Applications to Markov Decision Processes, A Universal Dynamic Program and Refined Existence Results for Decentralized Stochastic Control, Optimal Control of Partially Observable Piecewise Deterministic Markov Processes, Convergence of probability measures and Markov decision models with incomplete information, Average Cost Markov Decision Processes with Semi-Uniform Feller Transition Probabilities, Robustness to Approximations and Model Learning in MDPs and POMDPs, Unnamed Item, Uniform Fatou's lemma, Weak Feller property of non-linear filters, Fatou's Lemma for Weakly Converging Measures under the Uniform Integrability Condition, Strong Uniform Value in Gambling Houses and Partially Observable Markov Decision Processes, MDPs with setwise continuous transition probabilities, A Fenchel-Moreau-Rockafellar type theorem on the Kantorovich-Wasserstein space with applications in partially observable Markov decision processes, Robustness to Incorrect Priors in Partially Observed Stochastic Control, Stochastic Comparative Statics in Markov Decision Processes, Convergence for varying measures, Continuity of equilibria for two-person zero-sum games with noncompact action sets and unbounded payoffs, On the optimality equation for average cost Markov decision processes and its validity for inventory control
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Convergence of probability measures and Markov decision models with incomplete information
- An incomplete information inventory model with presence of inventories or backorders as only observations
- Berge's theorem for noncompact image sets
- Incomplete information in Markovian decision models
- Berge's maximum theorem for noncompact image sets
- Optimal control of partially observable Markovian systems
- Limiting Discounted-Cost Control of Partially Observable Stochastic Systems
- Optimization and Convergence of Observation Channels in Stochastic Control
- Average Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
- Partially Observed Inventory Systems: The Case of Rain Checks
- Zero-Sum Ergodic Stochastic Games with Feller Transition Probabilities
- 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
- Average Optimality in Dynamic Programming with General State Space
- Fatou's Lemma for Weakly Converging Probabilities
- Optimality Inequalities for Average Cost Markov Decision Processes and the Stochastic Cash Balance Problem
- Partially Observed Inventory Systems: The Case of Zero‐Balance Walk
- Discrete-Time Markovian Decision Processes with Incomplete State Observation