Actor-Critic Method for High Dimensional Static Hamilton--Jacobi--Bellman Partial Differential Equations based on Neural Networks (Q5021407): Difference between revisions

Latest revision as of 16:48, 27 July 2024

scientific article; zbMATH DE number 7456295

Language	Label	Description	Also known as
English	Actor-Critic Method for High Dimensional Static Hamilton--Jacobi--Bellman Partial Differential Equations based on Neural Networks	scientific article; zbMATH DE number 7456295

Statements

instance of

scholarly article

0 references

title

Actor-Critic Method for High Dimensional Static Hamilton--Jacobi--Bellman Partial Differential Equations based on Neural Networks (English)

0 references

0 references

0 references

0 references

SIAM Journal on Scientific Computing

0 references

publication date

13 January 2022

0 references

full work available at URL

https://arxiv.org/abs/2102.11379

0 references

zbMATH Keywords

Hamilton-Jacobi-Bellman equations

0 references

high dimensional partial differential equations

0 references

stochastic control

0 references

actor-critic methods

0 references

describes a project that uses

0 references

0 references

0 references

MaRDI publication profile

0 references

cites work

On the convergence rate of approximation schemes for Hamilton-Jacobi-Bellman Equations

0 references

Galerkin approximations of the generalized Hamilton-Jacobi-Bellman equation

0 references

Approximate solutions to the time-invariant Hamilton-Jacobi-Bellman equation

0 references

Deep optimal stopping

0 references

Natural actor-critic algorithms

0 references

Solving Dirichlet problems numerically using the Feynman-Kac representation

0 references

Machine learning for semi linear PDEs

0 references

User’s guide to viscosity solutions of second order partial differential equations

0 references

Tensor Decomposition Methods for High-dimensional Hamilton--Jacobi--Bellman Equations

0 references

Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations

0 references

Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning

0 references

Weak approximation of killed diffusion using Euler schemes.

0 references

Recurrent neural networks for stochastic control problems with delay

0 references

Solving high-dimensional partial differential equations using deep learning

0 references

Convergence of the deep BSDE method for coupled FBSDEs

0 references

Solving high-dimensional eigenvalue problems using deep neural networks: a diffusion Monte Carlo like approach

0 references

A derivative-free method for solving elliptic partial differential equations with deep neural networks

0 references

Polynomial Approximation of High-Dimensional Hamilton--Jacobi--Bellman Equations and Applications to Feedback Control of Semilinear Parabolic PDEs

0 references

Mitigating the curse of dimensionality: sparse grid characteristics method for optimal feedback control and HJB equations

0 references

Q5313290

0 references

OnActor-Critic Algorithms

0 references

HJB-POD-Based Feedback Design for the Optimal Control of Evolution Problems

0 references

On reachability and minimum cost optimal control

0 references

A time-dependent Hamilton-Jacobi formulation of reachable sets for continuous dynamic games

0 references

Overapproximating reachable sets by Hamilton-Jacobi projections

0 references

Adaptive Deep Learning for High-Dimensional Hamilton--Jacobi--Bellman Equations

0 references

Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space

0 references

Fronts propagating with curvature-dependent speed: Algorithms based on Hamilton-Jacobi formulations

0 references

Q4379369

0 references

Adapted solution of a backward stochastic differential equation

0 references

Q4029028

0 references

Probabilistic interpretation for systems of quasilinear parabolic partial differential equations

0 references

Neural networks-based backward scheme for fully nonlinear PDEs

0 references

Numerical solution of Hamilton–Jacobi–Bellman equations by an exponentially fitted finite volume method

0 references

Q4626283

0 references

Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem

0 references

Numerical solution of Hamilton-Jacobi-Bellman equations by an upwind finite volume method

0 references

Q4255599

0 references

Identifiers

zbMATH Open document ID

1481.65203

0 references

DOI

10.1137/21M1402303

0 references

Mathematics Subject Classification ID

0 references

0 references

0 references

0 references

0 references

0 references

0 references

0 references

0 references

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:5021407

@@ Property / author @@
-Jian-feng Lu
@@ Property / author: Jian-feng Lu / rank @@
-Normal rank
@@ Property / author @@
+Jian-feng Lu
@@ Property / author: Jian-feng Lu / rank @@
+Normal rank
@@ Property / Wikidata QID @@
+Q115246863
@@ Property / Wikidata QID: Q115246863 / rank @@
+Normal rank
@@ Property / describes a project that uses @@
+GitHub
@@ Property / describes a project that uses: GitHub / rank @@
+Normal rank
@@ Property / describes a project that uses @@
+TensorFlow
@@ Property / describes a project that uses: TensorFlow / rank @@
+Normal rank
@@ Property / describes a project that uses @@
+Adam
@@ Property / describes a project that uses: Adam / rank @@
+Normal rank
@@ Property / MaRDI profile type @@
+MaRDI publication profile
@@ Property / MaRDI profile type: MaRDI publication profile / rank @@
+Normal rank
@@ Property / arXiv ID @@
+.11379
@@ Property / arXiv ID: 2102.11379 / rank @@
+Normal rank
@@ Property / cites work @@
+On the convergence rate of approximation schemes for Hamilton-Jacobi-Bellman Equations
+Normal rank
@@ Property / cites work @@
+Galerkin approximations of the generalized Hamilton-Jacobi-Bellman equation
+Normal rank
@@ Property / cites work @@
+Approximate solutions to the time-invariant Hamilton-Jacobi-Bellman equation
+Normal rank
@@ Property / cites work @@
+Deep optimal stopping
@@ Property / cites work: Deep optimal stopping / rank @@
+Normal rank
@@ Property / cites work @@
+Natural actor-critic algorithms
@@ Property / cites work: Natural actor-critic algorithms / rank @@
+Normal rank
@@ Property / cites work @@
+Solving Dirichlet problems numerically using the Feynman-Kac representation
+Normal rank
@@ Property / cites work @@
+Machine learning for semi linear PDEs
@@ Property / cites work: Machine learning for semi linear PDEs / rank @@
+Normal rank
@@ Property / cites work @@
+User’s guide to viscosity solutions of second order partial differential equations
+Normal rank
@@ Property / cites work @@
+Tensor Decomposition Methods for High-dimensional Hamilton--Jacobi--Bellman Equations
+Normal rank
@@ Property / cites work @@
+Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
+Normal rank
@@ Property / cites work @@
+Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning
+Normal rank
@@ Property / cites work @@
+Weak approximation of killed diffusion using Euler schemes.
+Normal rank
@@ Property / cites work @@
+Recurrent neural networks for stochastic control problems with delay
+Normal rank
@@ Property / cites work @@
+Solving high-dimensional partial differential equations using deep learning
+Normal rank
@@ Property / cites work @@
+Convergence of the deep BSDE method for coupled FBSDEs
+Normal rank
@@ Property / cites work @@
+Solving high-dimensional eigenvalue problems using deep neural networks: a diffusion Monte Carlo like approach
+Normal rank
@@ Property / cites work @@
+A derivative-free method for solving elliptic partial differential equations with deep neural networks
+Normal rank
@@ Property / cites work @@
+Polynomial Approximation of High-Dimensional Hamilton--Jacobi--Bellman Equations and Applications to Feedback Control of Semilinear Parabolic PDEs
+Normal rank
@@ Property / cites work @@
+Mitigating the curse of dimensionality: sparse grid characteristics method for optimal feedback control and HJB equations
+Normal rank
@@ Property / cites work @@
+Q5313290
@@ Property / cites work: Q5313290 / rank @@
+Normal rank
@@ Property / cites work @@
+OnActor-Critic Algorithms
@@ Property / cites work: OnActor-Critic Algorithms / rank @@
+Normal rank
@@ Property / cites work @@
+HJB-POD-Based Feedback Design for the Optimal Control of Evolution Problems
+Normal rank
@@ Property / cites work @@
+On reachability and minimum cost optimal control
@@ Property / cites work: On reachability and minimum cost optimal control / rank @@
+Normal rank
@@ Property / cites work @@
+A time-dependent Hamilton-Jacobi formulation of reachable sets for continuous dynamic games
+Normal rank
@@ Property / cites work @@
+Overapproximating reachable sets by Hamilton-Jacobi projections
+Normal rank
@@ Property / cites work @@
+Adaptive Deep Learning for High-Dimensional Hamilton--Jacobi--Bellman Equations
+Normal rank
@@ Property / cites work @@
+Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
+Normal rank
@@ Property / cites work @@
+Fronts propagating with curvature-dependent speed: Algorithms based on Hamilton-Jacobi formulations
+Normal rank
@@ Property / cites work @@
+Q4379369
@@ Property / cites work: Q4379369 / rank @@
+Normal rank
@@ Property / cites work @@
+Adapted solution of a backward stochastic differential equation
+Normal rank
@@ Property / cites work @@
+Q4029028
@@ Property / cites work: Q4029028 / rank @@
+Normal rank
@@ Property / cites work @@
+Probabilistic interpretation for systems of quasilinear parabolic partial differential equations
+Normal rank
@@ Property / cites work @@
+Neural networks-based backward scheme for fully nonlinear PDEs
+Normal rank
@@ Property / cites work @@
+Numerical solution of Hamilton–Jacobi–Bellman equations by an exponentially fitted finite volume method
+Normal rank
@@ Property / cites work @@
+Q4626283
@@ Property / cites work: Q4626283 / rank @@
+Normal rank
@@ Property / cites work @@
+Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
+Normal rank
@@ Property / cites work @@
+Numerical solution of Hamilton-Jacobi-Bellman equations by an upwind finite volume method
+Normal rank
@@ Property / cites work @@
+Q4255599
@@ Property / cites work: Q4255599 / rank @@
+Normal rank
@@ links / mardi / name / links / mardi / name @@
+Publication:5021407