Stochastic control with signatures
Authors
- Bank, Peter
- Bayer, Christian
ORCID: 0000-0002-9116-0039 - Hager, Paul P.
- Riedel, Sebastian
- Nauen, Tobias
Keywords
- Stochastic optimal control, rough paths, signature
DOI
Abstract
This paper proposes to parameterize open loop controls in stochastic optimal control problems via suit- able classes of functionals depending on the driver's path signature, a concept adopted from rough path integration theory. We rigorously prove that these controls are dense in the class of progressively mea- surable controls and use rough path methods to establish suitable conditions for stability of the controlled dynamics and target functional. These results pave the way for Monte Carlo methods to stochastic optimal control for generic target functionals and dynamics. We discuss the rather versatile numerical algorithms for computing approximately optimal controls and verify their accurateness in benchmark problems from Mathematical Finance.
Download Documents