Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2603.01891 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912937292070912 |
|---|---|
| author | Nagy, C. F. Maximilian Celik, Onur Gospodinov, Emiliyan Seligmann, Florian Liao, Weiran Kaushik, Aryan Neumann, Gerhard |
| author_facet | Nagy, C. F. Maximilian Celik, Onur Gospodinov, Emiliyan Seligmann, Florian Liao, Weiran Kaushik, Aryan Neumann, Gerhard |
| contents | Action chunking can improve exploration and value estimation in long horizon reinforcement learning, but makes learning substantially harder since the critic must evaluate action sequences rather than single actions, greatly increasing approximation and data efficiency challenges. As a result, existing action chunking methods, primarily designed for the offline and offline-to-online settings, have not achieved strong performance in purely online reinforcement learning. We introduce SEAR, an off policy online reinforcement learning algorithm for action chunking. It exploits the temporal structure of action chunks and operates with a receding horizon, effectively combining the benefits of small and large chunk sizes. SEAR outperforms state of the art online reinforcement learning methods on Metaworld, training with chunk sizes up to 20. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01891 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SEAR: Sample Efficient Action Chunking Reinforcement Learning Nagy, C. F. Maximilian Celik, Onur Gospodinov, Emiliyan Seligmann, Florian Liao, Weiran Kaushik, Aryan Neumann, Gerhard Machine Learning Action chunking can improve exploration and value estimation in long horizon reinforcement learning, but makes learning substantially harder since the critic must evaluate action sequences rather than single actions, greatly increasing approximation and data efficiency challenges. As a result, existing action chunking methods, primarily designed for the offline and offline-to-online settings, have not achieved strong performance in purely online reinforcement learning. We introduce SEAR, an off policy online reinforcement learning algorithm for action chunking. It exploits the temporal structure of action chunks and operates with a receding horizon, effectively combining the benefits of small and large chunk sizes. SEAR outperforms state of the art online reinforcement learning methods on Metaworld, training with chunk sizes up to 20. |
| title | SEAR: Sample Efficient Action Chunking Reinforcement Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.01891 |