Robustness to Approximations and Model Learning in MDPs and POMDPs

DOI10.1007/978-3-030-76928-4_9zbMath1471.93255OpenAlexW3172003993MaRDI QIDQ5153607

Serdar Yüksel, Ali Devran Kara

Publication date: 30 September 2021

Published in: Modern Trends in Controlled Stochastic Processes: (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/1974/28913

zbMATH Keywords

Markov decision processesapproximate modelsPOMDPsrobust stochastic controlempirical learning

Mathematics Subject Classification ID

Sensitivity (robustness) (93B35) Markov and semi-Markov decision processes (90C40) Stochastic systems in control theory (general) (93E03)

Cites Work

• Adapted Wasserstein distances and stability in mathematical finance
• Near optimality of quantized policies in stochastic control under weak continuity conditions
• Connections between stochastic control and dynamic games
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• Robust properties of risk-sensitive control
• Bayesian nonparametrics
• Continuity of utility maximization under weak convergence
• Weak Feller property of non-linear filters
• Convergence Analysis for Distributionally Robust Optimization and Equilibrium Problems
• Partially Observable Total-Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
• Statistical Methods in Markov Chains
• Nonparametric Estimation of Conditional Distributions
• Minimax optimal control of stochastic uncertain systems with relative entropy constraints
• On the Asymptotic Optimality of Finite Approximations to Markov Decision Processes with Borel Spaces
• Real Analysis and Probability
• Average Optimality in Markov Control Processes via Discounted-Cost Problems and Linear Programming
• Robust H∞ infinity control in the presence of stochastic uncertainty
• Robustness to Incorrect System Models in Stochastic Control
• Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games
• Robustness to Incorrect Priors in Partially Observed Stochastic Control
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Robustness to Approximations and Model Learning in MDPs and POMDPs