In our recent work [3] we introduced the grid-sampling SDE as a proxy for modeling exploration in continuous-time reinforcement learning. In this note, we provide further motivation for the use of this SDE and discuss its wellposedness in the presence of jumps.
Cite
@article{arxiv.2410.07778,
title = {On the grid-sampling limit SDE},
author = {Christian Bender and Nguyen Tran Thuan},
journal= {arXiv preprint arXiv:2410.07778},
year = {2024}
}
Comments
This note provides supplementary materials to arXiv:2409.17200 in a self-contained way