Gradient flows for regularized stochastic control problems

DOI10.1137/20M1373645MaRDI QIDQ6576858zbMATH OpenFDO

Authors David Šiška, Lukasz Szpruch

Publication date 23 July 2024

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/20M1373645

zbMATH Keywords

backward stochastic differential equationgradient flowPontryagin optimalitystochastic control

Mathematics Subject Classification ID

Invariant measures for infinite-dimensional dissipative dynamical systems (37L40) Applications of stochastic analysis (to PDEs, etc.) (60H30) Optimal stochastic control (93E20)

Recommendations

• An efficient gradient projection method for stochastic optimal control problems
• An effective gradient projection method for stochastic optimal control
• Optimal control for a mixed flow of Hamiltonian and gradient type in space of probability measures (with Appendix B by Atanas Stefanov)

Cites work

• A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
• A learning scheme by sparse grids and Picard approximations for semilinear parabolic PDEs
• A modified MSA for stochastic control problems
• A neural network-based policy iteration algorithm with global \(H^2\)-superlinear convergence for stochastic games on domains
• A stability approach for solving multidimensional quadratic BSDEs
• Backward stochastic differential equations. From linear to fully nonlinear theory
• Central limit theorem for Markov processes with spectral gap in the Wasserstein metric
• Continuous exponential martingales and BMO
• Controlled Markov processes and viscosity solutions
• Coupling and exponential ergodicity for stochastic differential equations driven by Lévy processes
• Exploratory HJB equations and their convergence
• Exponential convergence and stability of Howard's policy improvement algorithm for controlled diffusions
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• scientific article; zbMATH DE number 3720745 (Why is no real title available?)
• scientific article; zbMATH DE number 1095138 (Why is no real title available?)
• scientific article; zbMATH DE number 3277871 (Why is no real title available?)
• Mean-field Langevin dynamics and energy landscape of neural networks
• Newton method for stochastic control problems
• Nonlinear stochastic evolution equations of second order with damping
• Probabilistic theory of mean field games with applications I. Mean field FBSDEs, control, and games
• Regularity and stability of feedback relaxed controls
• Reinforcement learning. An introduction
• Stochastic evolution equations
• Stochastic optimal control. The discrete time case
• Weak quantitative propagation of chaos via differential calculus on the space of measures

Cited in

(6)

• A fast iterative PDE-based algorithm for feedback controls of nonsmooth mean-field control problems
• The modified MSA, a gradient flow and convergence
• Mirror descent for stochastic control problems with measure-valued controls
• Entropy annealing for policy mirror descent in continuous time and space
• Backward stochastic control system with entropy regularization
• Entropic mean-field min-max problems via best response flow

This page was built for publication: Gradient flows for regularized stochastic control problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6576858)