Hit-and-Run for Sampling and Planning in Non-Convex Spaces

Yasin Abbasi-Yadkori, Peter Bartlett, Victor Gabillon, Alan Malek
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, PMLR 54:888-895, 2017.

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 this Paper

BibTeX
@InProceedings{pmlr-v54-abbasi-yadkori17a, title = {{Hit-and-Run for Sampling and Planning in Non-Convex Spaces}}, author = {Abbasi-Yadkori, Yasin and Bartlett, Peter and Gabillon, Victor and Malek, Alan}, booktitle = {Proceedings of the 20th International Conference on Artificial Intelligence and Statistics}, pages = {888--895}, year = {2017}, editor = {Singh, Aarti and Zhu, Jerry}, volume = {54}, series = {Proceedings of Machine Learning Research}, month = {20--22 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v54/abbasi-yadkori17a/abbasi-yadkori17a.pdf}, url = {https://proceedings.mlr.press/v54/abbasi-yadkori17a.html}, 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.} }
Endnote
%0 Conference Paper %T Hit-and-Run for Sampling and Planning in Non-Convex Spaces %A Yasin Abbasi-Yadkori %A Peter Bartlett %A Victor Gabillon %A Alan Malek %B Proceedings of the 20th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2017 %E Aarti Singh %E Jerry Zhu %F pmlr-v54-abbasi-yadkori17a %I PMLR %P 888--895 %U https://proceedings.mlr.press/v54/abbasi-yadkori17a.html %V 54 %X 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.
APA
Abbasi-Yadkori, Y., Bartlett, P., Gabillon, V. & Malek, A.. (2017). Hit-and-Run for Sampling and Planning in Non-Convex Spaces. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 54:888-895 Available from https://proceedings.mlr.press/v54/abbasi-yadkori17a.html.

Related Material