On the grid-sampling limit SDE
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913540148822016 |
|---|---|
| author | Bender, Christian Thuan, Nguyen Tran |
| author_facet | Bender, Christian Thuan, Nguyen Tran |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07778 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the grid-sampling limit SDE Bender, Christian Thuan, Nguyen Tran Machine Learning Probability Primary: 60H10, Secondary: 60G57, 93E35 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. |
| title | On the grid-sampling limit SDE |
| topic | Machine Learning Probability Primary: 60H10, Secondary: 60G57, 93E35 |
| url | https://arxiv.org/abs/2410.07778 |