Learning effective state-feedback controllers through efficient multilevel importance samplers

DOI10.1080/00207179.2018.1459857MaRDI QIDQ5240668zbMATH OpenOpenAlexWikidataFDO

Authors Hilbert J. Kappen

Publication date 29 October 2019

Published in International Journal of Control (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Full work available at URL https://doi.org/10.1080/00207179.2018.1459857

zbMATH Keywords

importance samplingmultilevel Monte Carlo methodpath integral control problems

Mathematics Subject Classification ID

Feedback control (93B52) Nonlinear systems in control theory (93C10) Optimal stochastic control (93E20)

Recommendations

• Adaptive importance sampling for control and inference
• A multilevel approach for stochastic nonlinear optimal control
• Control functionals for Monte Carlo integration
• Stochastic optimal control via forward and backward stochastic differential equations and importance sampling
• Importance sampling in path space for diffusion processes with slow-fast variables

Cites work

• A tutorial on the cross-entropy method
• Adaptive importance sampling for control and inference
• Multilevel Monte Carlo Path Simulation
• Optimal control as a graphical model inference problem
• Particle Smoothing for Hidden Diffusion Processes: Adaptive Path Integral Smoother

Cited in

(2)

• Adaptive importance sampling for control and inference
• A multilevel approach for stochastic nonlinear optimal control

This page was built for publication: Learning effective state-feedback controllers through efficient multilevel importance samplers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5240668)