An Algorithm to Construct Subsolutions of Convex Optimal Control Problems
From MaRDI portal
Publication:5039275
DOI10.1137/21M1402005zbMath1503.90152arXiv2103.00936OpenAlexW3135350760MaRDI QIDQ5039275
No author found.
Publication date: 12 October 2022
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2103.00936
dynamic programmingMarkov decision processdiscrete-time subsolutiondeterministic/stochastic optimal control
Dynamic programming in optimal control and differential games (49L20) Dynamic programming (90C39) Optimal stochastic control (93E20) Discrete approximations in optimal control (49M25)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Simulation of BSDEs with jumps by Wiener chaos expansion
- Overcoming the curse of dimensionality for some Hamilton-Jacobi partial differential equations via neural network architectures
- Max-plus methods for nonlinear control and estimation.
- Discrete dynamic programming and viscosity solutions of the Bellman equation
- Stochastic optimal control. The discrete time case
- Conjugate convex functions in optimal stochastic control
- CasADi: a software framework for nonlinear optimization and optimal control
- Neural networks-based backward scheme for fully nonlinear PDEs
- On some neural network architectures that can represent viscosity solutions of certain high dimensional Hamilton-Jacobi partial differential equations
- Duality-based a posteriori error estimates for some approximation schemes for optimal investment problems
- Simulation of BSDEs by Wiener chaos expansion
- Controlled Markov processes and viscosity solutions
- Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications
- Approximate Dynamic Programming
- Regression Methods for Stochastic Control Problems and Their Convergence Analysis
- An Iterative Procedure for Constructing Subsolutions of Discrete-Time Optimal Control Problems
- The Cutting-Plane Method for Solving Convex Programs
- Error bounds for monotone approximation schemes for parabolic Hamilton-Jacobi-Bellman equations
- Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning
- Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Convergence Analysis
- Semi-Lagrangian Approximation Schemes for Linear and Hamilton—Jacobi Equations
- Nonlinear Optimal Control via Occupation Measures and LMI-Relaxations
