Hit-and-Run for Sampling and Planning in Non-Convex Spaces
Abstract
We propose the Hit-and-Run algorithm for planning and sampling problems in non- convex spaces. For sampling, we show the first analysis of the Hit-and-Run algorithm in non-convex spaces and show that it mixes fast as long as certain smoothness conditions are satisfied. In particular, our analysis reveals an intriguing connection between fast mixing and the existence of smooth measure-preserving mappings from a convex space to the non-convex space. For planning, we show advantages of Hit-and- Run compared to state-of-the-art planning methods such as Rapidly-Exploring Random Trees.
Cite
Text
Abbasi-Yadkori et al. "Hit-and-Run for Sampling and Planning in Non-Convex Spaces." International Conference on Artificial Intelligence and Statistics, 2017.Markdown
[Abbasi-Yadkori et al. "Hit-and-Run for Sampling and Planning in Non-Convex Spaces." International Conference on Artificial Intelligence and Statistics, 2017.](https://mlanthology.org/aistats/2017/abbasiyadkori2017aistats-hit/)BibTeX
@inproceedings{abbasiyadkori2017aistats-hit,
title = {{Hit-and-Run for Sampling and Planning in Non-Convex Spaces}},
author = {Abbasi-Yadkori, Yasin and Bartlett, Peter L. and Gabillon, Victor and Malek, Alan},
booktitle = {International Conference on Artificial Intelligence and Statistics},
year = {2017},
pages = {888-895},
url = {https://mlanthology.org/aistats/2017/abbasiyadkori2017aistats-hit/}
}