Imagen de Portada

Operator-Theoretic Foundations and Policy Gradient Methods for General MDPs with Unbounded Costs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gupta, Abhishek, Mahajan, Aditya
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Optimization and Control 90C40, 47A55, 90C26, 93E35
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Policy stability and ultimate stationarity in discounted risk-sensitive stochastic control
por: Bäuerle, Nicole, et al.
Publicado: (2026)

Blackwell optimality and policy stability for long-run risk sensitive stochastic control
por: Bäuerle, Nicole, et al.
Publicado: (2024)

Markov Decision Processes of the Third Kind: Learning Distributions by Policy Gradient Descent
por: Bäuerle, Nicole, et al.
Publicado: (2026)

Convex Regularization and Convergence of Policy Gradient Flows under Safety Constraints
por: Malo, Pekka, et al.
Publicado: (2024)

Optimal Control of a Stochastic Power System -- Algorithms and Mathematical Analysis
por: Wang, Zhen, et al.
Publicado: (2024)

Average Cost Optimality of Partially Observed MDPS: Contraction of Non-linear Filters, Optimal Solutions and Approximations
por: Demirci, Yunus Emre, et al.
Publicado: (2023)

Beyond Bellman: High-Order Generator Regression for Continuous-Time Policy Evaluation
por: Zheng, Yaowei, et al.
Publicado: (2026)

Long run control of nonhomogeneous Markov processes
por: Stettner, Łukasz
Publicado: (2025)

A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces
por: Kerimkulov, Bekzhan, et al.
Publicado: (2023)

Characterizing nonconvex boundaries via scalarization
por: Ma, Jin, et al.
Publicado: (2025)

Existence of bounded solutions to multiplicative Poisson equations under mixing property
por: Pitera, Marcin, et al.
Publicado: (2023)

Deep Relaxation of Controlled Stochastic Gradient Descent via Singular Perturbations
por: Bardi, Martino, et al.
Publicado: (2022)

Large-Scale Minimization of the Pseudospectral Abscissa
por: Aliyev, Nicat, et al.
Publicado: (2022)

Gradient Norm Regularization Second-Order Algorithms for Solving Nonconvex-Strongly Concave Minimax Problems
por: Wang, Jun-Lin, et al.
Publicado: (2024)

Sample Complexity of Policy Gradient for Log-Growth Control
por: Pan, Qiuhua, et al.
Publicado: (2026)

Cost-optimal Management of a Residential Heating System With a Geothermal Energy Storage Under Uncertainty
por: Takam, Paul Honore, et al.
Publicado: (2025)

Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets
por: Li, Mengmeng, et al.
Publicado: (2023)

A Linear Parameter-Varying Framework for the Analysis of Time-Varying Optimization Algorithms
por: Jakob, Fabian, et al.
Publicado: (2025)

On the Practical Implementation of a Sequential Quadratic Programming Algorithm for Nonconvex Sum-of-squares Problems
por: Olucak, Jan, et al.
Publicado: (2026)

Measuring dissimilarity between convex cones by means of max-min angles
por: de Oliveira, Welington, et al.
Publicado: (2025)

State-Dependent Uncertainty Modeling in Robust Optimal Control Problems through Generalized Semi-Infinite Programming
por: Wehbeh, J., et al.
Publicado: (2025)

Sampled-Data Wasserstein Distributionally Robust Control of Multiplicative Systems: A Convex Relaxation with Performance Guarantees
por: Hsieh, Chung-Han
Publicado: (2026)

Application and issues in abstract convexity
por: Millán, Reinier Díaz, et al.
Publicado: (2022)

A multiscale Consensus-Based algorithm for multi-level optimization
por: Herty, Michael, et al.
Publicado: (2024)

Two trust region type algorithms for solving nonconvex-strongly concave minimax problems
por: Yao, Tongliang, et al.
Publicado: (2024)

A Fully Parameter-Free Second-Order Algorithm for Convex-Concave Minimax Problems
por: Wang, Junlin, et al.
Publicado: (2024)

Bounding-Focused Discretization Methods for the Global Optimization of Nonconvex Semi-Infinite Programs
por: Turan, Evren M., et al.
Publicado: (2023)

Designing Tractable Piecewise Affine Policies for Multi-Stage Adjustable Robust Optimization
por: Thomä, Simon, et al.
Publicado: (2022)

From Semi-Infinite Constraints to Structured Robust Policies: Optimal Gain Selection for Financial Systems
por: Hsieh, Chung-Han
Publicado: (2022)

On Strategic Measures and Optimality Properties in Discrete-Time Stochastic Control with Universally Measurable Policies
por: Yu, Huizhen
Publicado: (2022)

Multivariate approximation by polynomial and generalised rational functions
por: Millán, R. Díaz, et al.
Publicado: (2021)

Average-Cost MDPs with Infinite State and Action Sets: New Sufficient Conditions for Optimality Inequalities and Equations
por: Feinberg, Eugene A., et al.
Publicado: (2024)

Sparse Polynomial Optimization with Unbounded Sets
por: Huang, Lei, et al.
Publicado: (2024)

Projected Gradient Methods with Momentum
por: Lapucci, Matteo, et al.
Publicado: (2026)

Semi-Infinite Programs for Robust Control and Optimization: Efficient Solutions and Extensions to Existence Constraints
por: Wehbeh, Jad, et al.
Publicado: (2024)

Dual Spectral Projected Gradient Method for Generalized Log-det Semidefinite Programming
por: Namchaisiri, Charles, et al.
Publicado: (2024)

Benign landscapes of low-dimensional relaxations for orthogonal synchronization on general graphs
por: McRae, Andrew D., et al.
Publicado: (2023)

Polarized consensus-based dynamics for optimization and sampling
por: Bungert, Leon, et al.
Publicado: (2022)

Non-Expansive Mappings in Two-Time-Scale Stochastic Approximation: Finite-Time Analysis
por: Chandak, Siddharth
Publicado: (2025)

A Globally Convergent Gradient Method with Momentum
por: Lapucci, Matteo, et al.
Publicado: (2024)