Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.09614 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929385733357568 |
|---|---|
| author | Sequeira, André Santos, Luis Paulo Barbosa, Luis Soares |
| author_facet | Sequeira, André Santos, Luis Paulo Barbosa, Luis Soares |
| contents | This research explores the trainability of Parameterized Quantum circuit-based policies in Reinforcement Learning, an area that has recently seen a surge in empirical exploration. While some studies suggest improved sample complexity using quantum gradient estimation, the efficient trainability of these policies remains an open question. Our findings reveal significant challenges, including standard Barren Plateaus with exponentially small gradients and gradient explosion. These phenomena depend on the type of basis-state partitioning and mapping these partitions onto actions. For a polynomial number of actions, a trainable window can be ensured with a polynomial number of measurements if a contiguous-like partitioning of basis-states is employed. These results are empirically validated in a multi-armed bandit environment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09614 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Trainability issues in quantum policy gradients Sequeira, André Santos, Luis Paulo Barbosa, Luis Soares Quantum Physics Machine Learning This research explores the trainability of Parameterized Quantum circuit-based policies in Reinforcement Learning, an area that has recently seen a surge in empirical exploration. While some studies suggest improved sample complexity using quantum gradient estimation, the efficient trainability of these policies remains an open question. Our findings reveal significant challenges, including standard Barren Plateaus with exponentially small gradients and gradient explosion. These phenomena depend on the type of basis-state partitioning and mapping these partitions onto actions. For a polynomial number of actions, a trainable window can be ensured with a polynomial number of measurements if a contiguous-like partitioning of basis-states is employed. These results are empirically validated in a multi-armed bandit environment. |
| title | Trainability issues in quantum policy gradients |
| topic | Quantum Physics Machine Learning |
| url | https://arxiv.org/abs/2406.09614 |