Robustness to Incorrect Priors and Controlled Filter Stability in Partially Observed Stochastic Control

DOI10.1137/21M1417442zbMath1489.93137arXiv2110.03720OpenAlexW3205387731MaRDI QIDQ5071031

Curtis McDonald, Serdar Yüksel

Publication date: 19 April 2022

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2110.03720

zbMATH Keywords

robustnessnonlinear filteringpartially observed Markov decision processes (POMDPs)

Mathematics Subject Classification ID

Filtering in stochastic control theory (93E11) Observability (93B07) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Related Items (1)

Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic observability in network state estimation and control
• Stability of the filter equation for a time-dependent signal on \(\mathbb R^{d}\)
• Observability and nonlinear filtering
• The stability of conditional Markov processes and Markov chains in random environments
• Discrete time nonlinear filters with informative observations are stable
• A concept of local observability
• Incomplete information in Markovian decision models
• Exponential filter stability via Dobrushin's coefficient
• Weak Feller property of non-linear filters
• Uniform observability of hidden Markov models and filter stability for unstable signals
• On a role of predictor in the filtering stability
• A further remark on dynamic programming for partially observed Markov processes
• Dynamic programming for ergodic control with partial observations.
• A partial history of the early development of continuous-time nonlinear stochastic systems theory
• Partially Observable Total-Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
• Merging of Opinions with Increasing Information
• Observability of autonomous discrete time non-linear systems: a geometric approach
• Discrete-time filtering for linear systems with non-Gaussian initial conditions: asymptotic behavior of the difference between the MMSE and LMSE estimates
• Dual effect, certainty equivalence, and separation in stochastic control
• Reduction of a Controlled Markov Model with Incomplete Data to a Problem with Complete Information in the Case of Borel State and Control Space
• Nonlinear controllability and observability
• Average Cost Dynamic Programming Equations For Controlled Markov Chains With Partial Observations
• Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
• Robustness to Incorrect Priors in Partially Observed Stochastic Control
• Observability of linear stochastic uncertain systems
• Dynamic Programming for Ergodic Control of Markov Chains under Partial Observations: A Correction
• \(H^ \infty\)-optimal control and related minimax design problems. A dynamic game approach.

This page was built for publication: Robustness to Incorrect Priors and Controlled Filter Stability in Partially Observed Stochastic Control