Model-Free Stochastic Reachability Using Kernel Distribution Embeddings

Model-Free Stochastic Reachability Using Kernel Distribution Embeddings

We present a data-driven solution to the terminal-hitting stochastic reachability problem for a Markov control process. We employ a nonparametric representation of the stochastic kernel as a conditional distribution embedding within a reproducing kernel Hilbert space (RKHS). This representation avoi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE control systems letters Vol. 4; no. 2; pp. 512 - 517
Main Authors: Thorpe, Adam J., Oishi, Meeko M. K.
Format: Journal Article
Language:English
Published: IEEE 01-04-2020
Subjects:
Aerospace electronics
autonomous systems
Computational modeling
Dynamic programming
Hilbert space
Kernel
machine learning
Markov processes
Stochastic optimal control
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a data-driven solution to the terminal-hitting stochastic reachability problem for a Markov control process. We employ a nonparametric representation of the stochastic kernel as a conditional distribution embedding within a reproducing kernel Hilbert space (RKHS). This representation avoids intractable integrals in the dynamic recursion of the stochastic reachability problem since the expectations can be calculated as an inner product within the RKHS. We demonstrate this approach on a high-dimensional chain of integrators and on Clohessy-Wiltshire-Hill dynamics.
ISSN:2475-1456
2475-1456
DOI:10.1109/LCSYS.2019.2954102