Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.20538 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914817048051712 |
|---|---|
| author | Yang, Lingyi |
| author_facet | Yang, Lingyi |
| contents | Stability issues with reinforcement learning methods persist. To better understand some of these stability and convergence issues involving deep reinforcement learning methods, we examine a simple linear quadratic example. We interpret the convergence criterion of exact Q-learning in the sense of a monotone scheme and discuss consequences of function approximation on monotonicity properties. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20538 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Q-learning as a monotone scheme Yang, Lingyi Machine Learning Stability issues with reinforcement learning methods persist. To better understand some of these stability and convergence issues involving deep reinforcement learning methods, we examine a simple linear quadratic example. We interpret the convergence criterion of exact Q-learning in the sense of a monotone scheme and discuss consequences of function approximation on monotonicity properties. |
| title | Q-learning as a monotone scheme |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2405.20538 |