On the Interplay Between Sparsity and Training in Deep Reinforcement Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915132259434496 |
|---|---|
| author | Davelouis, Fatima Martin, John D. Bowling, Michael |
| author_facet | Davelouis, Fatima Martin, John D. Bowling, Michael |
| contents | We study the benefits of different sparse architectures for deep reinforcement learning. In particular, we focus on image-based domains where spatially-biased and fully-connected architectures are common. Using these and several other architectures of equal capacity, we show that sparse structure has a significant effect on learning performance. We also observe that choosing the best sparse architecture for a given domain depends on whether the hidden layer weights are fixed or learned. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16729 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On the Interplay Between Sparsity and Training in Deep Reinforcement Learning Davelouis, Fatima Martin, John D. Bowling, Michael Machine Learning Artificial Intelligence We study the benefits of different sparse architectures for deep reinforcement learning. In particular, we focus on image-based domains where spatially-biased and fully-connected architectures are common. Using these and several other architectures of equal capacity, we show that sparse structure has a significant effect on learning performance. We also observe that choosing the best sparse architecture for a given domain depends on whether the hidden layer weights are fixed or learned. |
| title | On the Interplay Between Sparsity and Training in Deep Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2501.16729 |