Imagen de Portada

Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Giegrich, Michael, Reisinger, Christoph, Zhang, Yufei
Formato:	Preprint
Publicado:	2022
Materias:	Optimization and Control Machine Learning 68Q25, 93E20
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Infinite time horizon stochastic recursive control problems with jumps: dynamic programming and stochastic verification theorems
por: Luo, Sheng, et al.
Publicado: (2024)

Stochastic linear-quadratic differential game with Markovian jumps in an infinite horizon
por: Wu, Fan, et al.
Publicado: (2024)

Mean--Variance Portfolio Selection by Continuous-Time Reinforcement Learning: Algorithms, Regret Analysis, and Empirical Study
por: Huang, Yilie, et al.
Publicado: (2024)

Mirror Descent for Stochastic Control Problems with Measure-valued Controls
por: Kerimkulov, Bekzhan, et al.
Publicado: (2024)

Optimal control of SDEs with merely measurable drift: an HJB approach
por: Du, Kai, et al.
Publicado: (2025)

Convergence of Proximal Policy Gradient Method for Problems with Control Dependent Diffusion Coefficients
por: Davey, Ashley, et al.
Publicado: (2025)

Stochastic linear quadratic optimal control problems with regime-switching jumps in infinite horizon
por: Wu, Fan, et al.
Publicado: (2024)

Entropy annealing for policy mirror descent in continuous time and space
por: Sethi, Deven, et al.
Publicado: (2024)

Convergence and turnpike properties of linear-quadratic mean field control problems with common noise
por: Bayraktar, Erhan, et al.
Publicado: (2026)

Physics-informed approach for exploratory Hamilton--Jacobi--Bellman equations via policy iterations
por: Kim, Yeongjong, et al.
Publicado: (2025)

Model-free policy gradient for discrete-time mean-field control
por: Meunier, Matthieu, et al.
Publicado: (2026)

Turnpike and dissipativity in generalized discrete-time stochastic linear-quadratic optimal control
por: Schießl, Jonas, et al.
Publicado: (2023)

Controllability and Vector Potential
por: Shankar, Shiva
Publicado: (2019)

Optimistic Training and Convergence of Q-Learning -- Extended Version
por: Mehta, Prashant, et al.
Publicado: (2026)

Open-loop and closed-loop solvabilities for zero-sum stochastic linear quadratic differential games of Markovian regime switching system
por: Wu, Fan, et al.
Publicado: (2024)

Control randomisation approach for policy gradient and application to reinforcement learning in optimal switching
por: Denkert, Robert, et al.
Publicado: (2024)

A system of Schrödinger's problems and functional equations
por: Mikami, Toshio, et al.
Publicado: (2025)

Does DQN Learn?
por: Gopalan, Aditya, et al.
Publicado: (2022)

Neural Actor-Critic Methods for Hamilton-Jacobi-Bellman PDEs: Asymptotic Analysis and Numerical Studies
por: Cohen, Samuel N., et al.
Publicado: (2025)

Impulse control maximising average cost per unit time: a non-uniformly ergodic case
por: Palczewski, Jan, et al.
Publicado: (2016)

Ergodicity and turnpike properties of linear-quadratic mean field control problems
por: Bayraktar, Erhan, et al.
Publicado: (2025)

A fast iterative PDE-based algorithm for feedback controls of nonsmooth mean-field control problems
por: Reisinger, Christoph, et al.
Publicado: (2021)

Reflected stochastic recursive control problems with jumps: dynamic programming and stochastic verification theorems
por: Liu, Lu, et al.
Publicado: (2025)

Two person non-zero-sum linear-quadratic differential game with Markovian jumps in infinite horizon
por: Wu, Fan, et al.
Publicado: (2024)

On the hardness of deciding the finite convergence of Lasserre hierarchies
por: Vargas, Luis Felipe
Publicado: (2024)

Quantum stochastic linear quadratic control theory: Closed-loop solvability
por: Penghui, Wang, et al.
Publicado: (2025)

A local maximum principle for robust optimal control problems of quadratic BSDEs
por: Hao, Tao, et al.
Publicado: (2024)

Optimal control of stochastic networks of $M/M/\infty$ queues with linear costs
por: Carratelli, Giovanni Pugliese, et al.
Publicado: (2025)

Stability and Sensitivity Analysis of Relative Temporal-Difference Learning: Extended Version
por: Sakha, Masoud S., et al.
Publicado: (2026)

Stabilization via localized controls in nonlocal models of crowd dynamics
por: Pogodaev, Nikolay, et al.
Publicado: (2024)

Optimal control, viscosity approximation and Arrhenius Law for the shallow lake problem
por: Koutsimpela, Angeliki, et al.
Publicado: (2024)

Optimal control of a non-smooth elliptic PDE with non-linear term acting on the control
por: Betz, Livia
Publicado: (2024)

Which exceptional low-dimensional projections of a Gaussian point cloud can be found in polynomial time?
por: Montanari, Andrea, et al.
Publicado: (2024)

Optimal Control of Unbounded Functional Stochastic Evolution Systems in Hilbert Spaces: Second-Order Path-dependent HJB Equation
por: Tang, Shanjian, et al.
Publicado: (2024)

Quantitative Fattorini-Hautus test and minimal null control time for parabolic problems
por: Khodja, F. Ammar, et al.
Publicado: (2024)

Stochastic Optimal Impulse Controls with Changing Running Costs
por: Cao, Yuchen, et al.
Publicado: (2025)

Convergence of Momentum-Based Optimization Algorithms with Time-Varying Parameters
por: Vidyasagar, Mathukumalli
Publicado: (2025)

Near Optimality of Lipschitz and Smooth Policies in Controlled Diffusions
por: Pradhan, Somnath, et al.
Publicado: (2024)

Path integral control under McKean-Vlasov dynamics
por: Bennett, Timothy
Publicado: (2024)

Stability of long run functionals with respect to stationary Markov controls
por: Stettner, Lukasz
Publicado: (2024)