Path Integral Control by Reproducing Kernel Hilbert Space Embedding
Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. Pages 1628-1633.
Abstract
We present an embedding of stochastic optimal control problems, of the so called path integral form, into reproducing kernel Hilbert spaces. Using consistent, sample based estimates of the embedding leads to a model-free, non-parametric approach for calculation of an approximate solution to the control problem. This formulation admits a decomposition of the problem into an invariant and task dependent component. Consequently, we make much more efficient use of the sample data compared to previous sample based approaches in this domain, e.g., by allowing sample re-use across tasks. Numerical examples on test problems, which illustrate the sample efficiency, are provided.
@inproceedings{ijcai2013p242,
title = {Path Integral Control by Reproducing Kernel Hilbert Space Embedding},
author = {Rawlik, Konrad and Toussaint, Marc and Vijayakumar, Sethu},
booktitle = {Proceedings of the Twenty-Third International Joint Conference on
Artificial Intelligence, {IJCAI-13}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Francesca Rossi},
pages = {1628--1633},
year = {2013},
month = {8},
url = {https://ijcai.org/proceedings/2013/242},
}
TY - CPAPER TI - Path Integral Control by Reproducing Kernel Hilbert Space Embedding AU - Rawlik, Konrad AU - Toussaint, Marc AU - Vijayakumar, Sethu T2 - Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, IJCAI-13 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2013 SP - 1628 EP - 1633 UR - https://ijcai.org/proceedings/2013/242 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
