Buchumschlag

Discretization error from regularized Reinforcement Learning to continuous-time stochastic control

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Pham, Huyên, Zhang, Yuming Paul, Zhu, Yuhua
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Optimization and Control
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Optimal-PhiBE: A PDE-based Model-free framework for Continuous-time Reinforcement Learning
von: Zhu, Yuhua, et al.
Veröffentlicht: (2025)

Full error analysis of policy gradient learning algorithms for exploratory linear quadratic mean-field control problem in continuous time with common noise
von: Frikha, Noufel, et al.
Veröffentlicht: (2024)

Discrete time stochastic impulse control with delay
von: Hamadène, Said, et al.
Veröffentlicht: (2025)

A randomisation method for mean-field control problems with common noise
von: Denkert, Robert, et al.
Veröffentlicht: (2024)

Optimal control of McKean-Vlasov systems under partial observation and hidden Markov switching
von: Fuhrman, Marco, et al.
Veröffentlicht: (2026)

Non-Exchangeable Mean Field Markov Decision Processes with common noise : from Bellman equation to quantitative propagation of chaos
von: Mekkaoui, Samy, et al.
Veröffentlicht: (2026)

Mean-field neural networks-based algorithms for McKean-Vlasov control problems *
von: Pham, Huyên, et al.
Veröffentlicht: (2022)

On Bellman equations for continuous-time policy evaluation I: discretization and approximation
von: Mou, Wenlong, et al.
Veröffentlicht: (2024)

Linear-quadratic optimal control for non-exchangeable mean-field SDEs and applications to systemic risk
von: de Crescenzo, Anna, et al.
Veröffentlicht: (2025)

A note on first-order and transversality conditions in infinite-horizon continuous-time optimal control models
von: Bosi, Stefano, et al.
Veröffentlicht: (2026)

Robust policy iteration for continuous-time stochastic $H_\infty$ control problem with unknown dynamics
von: Sun, Zhongshi, et al.
Veröffentlicht: (2024)

Discrete-time linear quadratic stochastic control with equality-constrained inputs: Application to energy demand response
von: Seugnet, Leo, et al.
Veröffentlicht: (2026)

PhiBE: A PDE-based Bellman Equation for Continuous Time Policy Evaluation
von: Zhu, Yuhua
Veröffentlicht: (2024)

Learning operators on labelled conditional distributions with applications to mean field control of non exchangeable systems
von: Mekkaoui, Samy, et al.
Veröffentlicht: (2026)

Safe continual learning in model predictive control with prescribed bounds on the tracking error
von: Lanza, Lukas, et al.
Veröffentlicht: (2023)

Reinforcement Learning for Discrete-time LQG Mean Field Social Control Problems with Unknown Dynamics
von: Zhang, Hanfang, et al.
Veröffentlicht: (2025)

Learning-based primal-dual optimal control of discrete-time stochastic systems with multiplicative noise
von: Jiang, Xiushan, et al.
Veröffentlicht: (2025)

Linear quadratic control for discrete-time systems with stochastic and bounded noises
von: Ma, Xuehui, et al.
Veröffentlicht: (2025)

Consistent inverse optimal control for discrete-time nonlinear stochastic systems
von: Wang, Ziliang, et al.
Veröffentlicht: (2025)

A fast continuous time approach for non-smooth convex optimization with time scaling and Tikhonov regularization
von: Csetnek, Robert Ernö, et al.
Veröffentlicht: (2022)

A unified optimal control framework: time-optimal control and stochastic optimal control
von: Yang, Shuzhen
Veröffentlicht: (2025)

The radius of metric regularity at infinity
von: Nguyen, Tung Minh, et al.
Veröffentlicht: (2025)

SVD-based factored-form Cubature Kalman Filtering for continuous-time stochastic systems with discrete measurements
von: Kulikova, Maria V., et al.
Veröffentlicht: (2024)

Faster stochastic cubic regularized Newton methods with momentum
von: Yang, Yiming, et al.
Veröffentlicht: (2025)

Discrete time optimal control with frequency constraints for non-smooth systems
von: Kotpalliwar, Shruti, et al.
Veröffentlicht: (2019)

Learning Generative Dynamics with Soft Law Constraints: A McKean-Vlasov FBSDE Approach
von: Boustany, Samer El, et al.
Veröffentlicht: (2026)

Fine-tuning of diffusion models via stochastic control: entropy regularization and beyond
von: Tang, Wenpin, et al.
Veröffentlicht: (2024)

Optimal control of continuous-time symmetric systems with unknown dynamics and noisy measurements
von: Taghavian, Hamed, et al.
Veröffentlicht: (2024)

A novel trajectory optimization algorithm for continuous-time model predictive control
von: Das, Souvik, et al.
Veröffentlicht: (2023)

Data-driven control of continuous-time systems: A synthesis-operator approach
von: Wakaiki, Masashi
Veröffentlicht: (2025)

Accuracy of Discretely Sampled Stochastic Policies in Continuous-time Reinforcement Learning
von: Jia, Yanwei, et al.
Veröffentlicht: (2025)

Convergence of continuous-time stochastic gradient descent with applications to deep neural networks
von: Lugosi, Gabor, et al.
Veröffentlicht: (2024)

When sampling works in data-driven control: Informativity for stabilization in continuous time
von: Eising, Jaap, et al.
Veröffentlicht: (2023)

Analysis of the vanishing discount limit for optimal control problems in continuous and discrete time
von: Cannarsa, Piermarco, et al.
Veröffentlicht: (2023)

The minimal hitting probability of continuous-time controlled Markov systems with countable states
von: Li, Yanyun, et al.
Veröffentlicht: (2024)

Modified global finite-time quasi-continuous second-order robust feedback control
von: Ruderman, Michael, et al.
Veröffentlicht: (2025)

Bridging Schrödinger and Bass: A Semimartingale Optimal Transport Problem with Diffusion Control
von: Henry-Labordere, Pierre, et al.
Veröffentlicht: (2026)

Model-free stochastic linear quadratic control for discrete-time systems with multiplicative and additive noises via semidefinite programming
von: Guo, Jing, et al.
Veröffentlicht: (2025)

A continuous-time fundamental lemma and its application in data-driven optimal control
von: Schmitz, Philipp, et al.
Veröffentlicht: (2024)

Multiparametric continuous-time optimal control via Pontryagin's Maximum Principle: explicit solutions and comparisons with discrete-time formulations
von: Lamakani, Lida, et al.
Veröffentlicht: (2026)