Copertina

Robustness to Model Approximation, Model Learning From Data, and Sample Complexity in Wasserstein Regular MDPs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhou, Yichen, Song, Yanglei, Yüksel, Serdar
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Systems and Control Optimization and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Partially Observed Optimal Stochastic Control: Regularity, Optimality, Approximations, and Learning
di: Kara, Ali Devran, et al.
Pubblicazione: (2024)

Near Optimal Approximations and Finite Memory Policies for POMPDs with Continuous Spaces
di: Kara, Ali Devran, et al.
Pubblicazione: (2024)

Quantizer Design for Finite Model Approximations, Model Learning, and Quantized Q-Learning for MDPs with Unbounded Spaces
di: Bicer, Osman, et al.
Pubblicazione: (2025)

Data-Driven Non-Parametric Model Learning and Adaptive Control of MDPs with Borel spaces: Identifiability and Near Optimal Design
di: Mrani-Zentar, Omar, et al.
Pubblicazione: (2025)

Quantum Markov Decision Processes: General Theory, Approximations, and Classes of Policies
di: Saldi, Naci, et al.
Pubblicazione: (2024)

Kernel Mean Embedding Topology: Weak and Strong Forms for Stochastic Kernels and Implications for Model Learning
di: Saldi, Naci, et al.
Pubblicazione: (2025)

Q-Learning for Stochastic Control under General Information Structures and Non-Markovian Environments
di: Kara, Ali Devran, et al.
Pubblicazione: (2023)

Another Look at Partially Observed Optimal Stochastic Control: Existence, Ergodicity, and Approximations without Belief-Reduction
di: Yüksel, Serdar
Pubblicazione: (2023)

Quantum Markov Decision Processes: Dynamic and Semi-Definite Programs for Optimal Solutions
di: Saldi, Naci, et al.
Pubblicazione: (2024)

Robust Decentralized Control of Coupled Systems via Risk Sensitive Control of Decoupled or Simple Models with Measure Change
di: Selk, Zachary, et al.
Pubblicazione: (2024)

Robust Feedback Optimization with Model Uncertainty: A Regularization Approach
di: Chan, Winnie, et al.
Pubblicazione: (2025)

Distributionally Robust Density Control with Wasserstein Ambiguity Sets
di: Pilipovsky, Joshua, et al.
Pubblicazione: (2024)

On Borkar and Young Relaxed Control Topologies and Continuous Dependence of Invariant Measures on Control Policy
di: Yüksel, Serdar
Pubblicazione: (2023)

Model approximation in MDPs with unbounded per-step cost
di: Bozkurt, Berk, et al.
Pubblicazione: (2024)

Wasserstein Distributionally Robust Regret-Optimal Control in the Infinite-Horizon
di: Kargin, Taylan, et al.
Pubblicazione: (2023)

Linear Dynamics meets Linear MDPs: Closed-Form Optimal Policies via Reinforcement Learning
di: Makdah, Abed AlRahman Al, et al.
Pubblicazione: (2025)

Wasserstein Distributionally Robust Control and State Estimation for Partially Observable Linear Systems
di: Jang, Minhyuk, et al.
Pubblicazione: (2024)

Mixed Regular and Impulsive Sampled-data LQR
di: Daafouz, Jamal, et al.
Pubblicazione: (2024)

Centralized Reduction of Decentralized Stochastic Control Models and their weak-Feller Regularity
di: Mrani-Zentar, Omar, et al.
Pubblicazione: (2024)

Robust Aperiodic Sampled-Data Washout Control for Uncertain Affine Systems
di: Giorgetti, Folco, et al.
Pubblicazione: (2025)

Sampled-Data Primal-Dual Gradient Dynamics in Model Predictive Control
di: Moriyasu, Ryuta, et al.
Pubblicazione: (2024)

Data-Driven Regularized Time-Limited h2 Model Reduction from Noisy Impulse Responses
di: Sakamoto, Hiroki, et al.
Pubblicazione: (2026)

Wasserstein Distributionally Robust Nash Equilibrium Seeking with Heterogeneous Data: A Lagrangian Approach
di: Wang, Zifan, et al.
Pubblicazione: (2025)

SLAM as a Stochastic Control Problem with Partial Information: Optimal Solutions and Rigorous Approximations
di: Gusija, Ilir, et al.
Pubblicazione: (2026)

A Saddle Point Algorithm for Robust Data-Driven Factor Model Problems
di: Khodakaramzadeh, Shabnam, et al.
Pubblicazione: (2025)

Performance guaranteed MPC Policy Approximation via Cost Guided Learning
di: Zhou, Chenchen, et al.
Pubblicazione: (2026)

Feasibility Analysis and Regularity Characterization of Distributionally Robust Safe Stabilizing Controllers
di: Mestres, Pol, et al.
Pubblicazione: (2023)

Subjective Equilibria under Beliefs of Exogenous Uncertainty: Linear Quadratic Case
di: Arslan, Gürdal, et al.
Pubblicazione: (2024)

Sample Complexity of Chance Constrained Optimization in Dynamic Environment
di: Shukla, Apurv, et al.
Pubblicazione: (2024)

On the Effect of Quadratic Regularization in Direct Data-Driven LQR
di: Klädtke, Manuel, et al.
Pubblicazione: (2026)

Learning Quasi-LPV Models and Robust Control Invariant Sets with Reduced Conservativeness
di: Mulagaleti, Sampath Kumar, et al.
Pubblicazione: (2025)

Robust MPC for Uncertain Linear Systems -- Combining Model Adaptation and Iterative Learning
di: Petrenz, Hannes, et al.
Pubblicazione: (2025)

Efficient Uncertainty Propagation with Guarantees in Wasserstein Distance
di: Figueiredo, Eduardo, et al.
Pubblicazione: (2025)

Sample-Based Piecewise Linear Power Flow Approximations Using Second-Order Sensitivities
di: Buason, Paprapee, et al.
Pubblicazione: (2025)

Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity
di: Zhang, Runyu, et al.
Pubblicazione: (2023)

Multiple Joint Chance Constraints Approximation for Uncertainty Modeling in Dispatch Problems
di: Wen, Yilin, et al.
Pubblicazione: (2024)

Regularization for Covariance Parameterization of Direct Data-Driven LQR Control
di: Zhao, Feiran, et al.
Pubblicazione: (2025)

Adversarial Reinforcement Learning for Robust Control of Fixed-Wing Aircraft under Model Uncertainty
di: Marquis, Dennis J., et al.
Pubblicazione: (2025)

Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games with Local Control and Global State Information
di: Yongacoglu, Bora, et al.
Pubblicazione: (2019)

Approximate Simulation-Based Verification of Compatibility of the Friedkin-Johnsen Model with Binary Observations
di: Xing, Yu, et al.
Pubblicazione: (2026)