Why long model-based rollouts are no reason for bad Q-value estimates
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916326322208768 |
|---|---|
| author | Wissmann, Philipp Hein, Daniel Udluft, Steffen Tresp, Volker |
| author_facet | Wissmann, Philipp Hein, Daniel Udluft, Steffen Tresp, Volker |
| contents | This paper explores the use of model-based offline reinforcement learning with long model rollouts. While some literature criticizes this approach due to compounding errors, many practitioners have found success in real-world applications. The paper aims to demonstrate that long rollouts do not necessarily result in exponentially growing errors and can actually produce better Q-value estimates than model-free methods. These findings can potentially enhance reinforcement learning techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11751 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Why long model-based rollouts are no reason for bad Q-value estimates Wissmann, Philipp Hein, Daniel Udluft, Steffen Tresp, Volker Machine Learning This paper explores the use of model-based offline reinforcement learning with long model rollouts. While some literature criticizes this approach due to compounding errors, many practitioners have found success in real-world applications. The paper aims to demonstrate that long rollouts do not necessarily result in exponentially growing errors and can actually produce better Q-value estimates than model-free methods. These findings can potentially enhance reinforcement learning techniques. |
| title | Why long model-based rollouts are no reason for bad Q-value estimates |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2407.11751 |