Cover Image

Deep neural networks can provably solve Bellman equations for Markov decision processes without the curse of dimensionality

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jentzen, Arnulf, Kleinberg, Konrad, Kruse, Thomas
Format:	Preprint
Published:	2025
Subjects:	Optimization and Control Machine Learning Numerical Analysis Probability 90C40, 90C39, 60J05, 93E20, 65C05, 68T07
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

Linear programming for finite-horizon vector-valued Markov decision processes
by: Mifrani, Anas, et al.
Published: (2025)

A Deterministic and Linear Model of Dynamic Optimization
by: Lahiri, Somdeb
Published: (2025)

Linear models of dynamic optimization with linear constraints
by: Lahiri, Somdeb
Published: (2025)

Sharp Bounds for Generalized Zagreb Indices of Graphs
by: Vaidya, Sanju, et al.
Published: (2024)

Entropic Risk-Averse Generalized Momentum Methods
by: Can, Bugra, et al.
Published: (2022)

An exponentially stable discrete-time primal-dual algorithm for distributed constrained optimization
by: Ren, Xiaoxing, et al.
Published: (2025)

Continuity of Filters for Discrete-Time Control Problems Defined by Explicit Equations
by: Feinberg, Eugene A., et al.
Published: (2023)

Games on deBruijn Graphs and Cycle Means
by: Drenska, Nadejda
Published: (2026)

Efficient spectral bounds on the chromatic number of Hamming, Johnson, and Kneser graph powers
by: Steinke, Finn A., et al.
Published: (2026)

Anderson Accelerated Primal-Dual Hybrid Gradient for solving LP
by: Zhou, Yingxin, et al.
Published: (2025)

Dual dynamic programming for stochastic programs over an infinite horizon
by: Ju, Caleb, et al.
Published: (2023)

IP Models for Minimum Zero Forcing Sets, Forts, and Related Graph Parameters
by: Cameron, Thomas R., et al.
Published: (2025)

The SCIP Optimization Suite 9.0
by: Bolusani, Suresh, et al.
Published: (2024)

The SCIP Optimization Suite 10.0
by: Hojny, Christopher, et al.
Published: (2025)

Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense
by: Ackermann, Julia, et al.
Published: (2023)

Stochastic dynamic programming with non-linear discounting
by: Bäuerle, Nicole, et al.
Published: (2020)

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

The vector linear program solver Bensolve -- notes on theoretical background
by: Löhne, Andreas, et al.
Published: (2015)

Equivalence between polyhedral projection, multiple objective linear programming and vector linear programming
by: Löhne, Andreas, et al.
Published: (2015)

Convergence of Neural Network Policies for Risk--Reward Optimization
by: Chen, Chang, et al.
Published: (2026)

Fixed Topology Minimum-Length Trees with Neighborhoods
by: Blanco, Víctor, et al.
Published: (2024)

An Augmented Lagrangian Method for Training Recurrent Neural Networks
by: Wang, Yue, et al.
Published: (2024)

Further results on the lower bound on reduced Zagreb index of trees
by: Bašić, Milan, et al.
Published: (2026)

Effectively Leveraging Momentum Terms in Stochastic Line Search Frameworks for Fast Optimization of Finite-Sum Problems
by: Lapucci, Matteo, et al.
Published: (2024)

Convergence Conditions for Stochastic Line Search Based Optimization of Over-parametrized Models
by: Lapucci, Matteo, et al.
Published: (2024)

HPR-LP: An implementation of an HPR method for solving linear programming
by: Chen, Kaihuang, et al.
Published: (2024)

Difference of Convex (DC) approach for neural network approximation with uniform loss function
by: Peiris, Vinesha, et al.
Published: (2026)

On Difference-of-SOS and Difference-of-Convex-SOS Decompositions for Polynomials
by: Niu, Yi-Shuai, et al.
Published: (2018)

Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for space-time solutions of semilinear partial differential equations
by: Ackermann, Julia, et al.
Published: (2024)

On Solution Uniqueness and Robust Recovery for Sparse Regularization with a Gauge: from Dual Point of View
by: He, Jiahuan, et al.
Published: (2023)

New Formulation for Coloring Circle Graphs and its Application to Capacitated Stowage Stack Minimization
by: Tanaka, Masato, et al.
Published: (2021)

Improved semidefinite programming bounds for the maximum $k$-colorable subgraph problem
by: Barkel, Mathijs, et al.
Published: (2026)

Structure, Analysis, and Synthesis of First-Order Algorithms
by: Miller, Jared, et al.
Published: (2026)

Extending graph total colorings to cell complexes
by: Dejter, Italo J.
Published: (2026)

A Game Theoretic Treatment of Contagion in Trade Networks
by: McAlister, John S., et al.
Published: (2025)

Improved Bounds for the Ultimate Independence Ratio of Odd Wheels
by: Clow, Alexander, et al.
Published: (2025)

A New Two-dimensional Model-based Subspace Method for Large-scale Unconstrained Derivative-free Optimization: 2D-MoSub
by: Xie, Pengcheng, et al.
Published: (2023)