Robustness to approximations and model learning in MDPs and POMDPs

DOI10.1007/978-3-030-76928-4_9zbMATH Open1471.93255OpenAlexW3172003993MaRDI QIDQ5153607FDOQ5153607

Authors: 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

Recommendations

• Robustness to incorrect system models in stochastic control
• Robustness to incorrect models and data-driven learning in average-cost optimal stochastic control
• Robustness to Incorrect Priors in Partially Observed Stochastic Control
• Stochastic Control with Imperfect Models
• Robustness to incorrect priors and controlled filter stability in partially observed stochastic control

zbMATH Keywords

Markov decision processesPOMDPsapproximate modelsrobust 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

• Title not available (Why is that?)
• Real Analysis and Probability
• Title not available (Why is that?)
• Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games
• Bayesian nonparametrics
• Average Optimality in Markov Control Processes via Discounted-Cost Problems and Linear Programming
• Connections between stochastic control and dynamic games
• Statistical Methods in Markov Chains
• Title not available (Why is that?)
• Nonparametric Estimation of Conditional Distributions
• Title not available (Why is that?)
• Robust H∞ infinity control in the presence of stochastic uncertainty
• On the asymptotic optimality of finite approximations to Markov decision processes with Borel spaces
• Partially observable total-cost Markov decision processes with weakly continuous transition probabilities
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• Convergence analysis for distributionally robust optimization and equilibrium problems
• Minimax optimal control of stochastic uncertain systems with relative entropy constraints
• Robust properties of risk-sensitive control
• Adapted Wasserstein distances and stability in mathematical finance
• Near optimality of quantized policies in stochastic control under weak continuity conditions
• Title not available (Why is that?)
• Robustness to incorrect system models in stochastic control
• Continuity of utility maximization under weak convergence
• Robustness to Incorrect Priors in Partially Observed Stochastic Control
• Weak Feller property of non-linear filters

Cited In (6)

• Robustness to incorrect models and data-driven learning in average-cost optimal stochastic control
• Robustness to incorrect system models in stochastic control
• Bottom-up learning of hierarchical models in a class of deterministic pomdp environments
• Introduction to internally consistent modeling, aggregation, inference, and policy
• Robustness to incorrect priors and controlled filter stability in partially observed stochastic control
• Another look at partially observed optimal stochastic control: existence, ergodicity, and approximations without belief-reduction

This page was built for publication: Robustness to approximations and model learning in MDPs and POMDPs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5153607)