Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2603.06413 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911493326372864 |
|---|---|
| author | Liu, Xiaoran David, Istvan |
| author_facet | Liu, Xiaoran David, Istvan |
| contents | The surge in reinforcement learning (RL) applications gave rise to diverse supporting technology, such as RL frameworks. However, the architectural patterns of these frameworks are inconsistent across implementations and there exists no reference architecture (RA) to form a common basis of comparison, evaluation, and integration. To address this gap, we propose an RA of RL frameworks. Through a grounded theory approach, we analyze 18 state-of-the-practice RL frameworks and, by that, we identify recurring architectural components and their relationships, and codify them in an RA. To demonstrate our RA, we reconstruct characteristic RL patterns. Finally, we identify architectural trends, e.g., commonly used components, and outline paths to improving RL frameworks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06413 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Reference Architecture of Reinforcement Learning Frameworks Liu, Xiaoran David, Istvan Software Engineering Artificial Intelligence Machine Learning The surge in reinforcement learning (RL) applications gave rise to diverse supporting technology, such as RL frameworks. However, the architectural patterns of these frameworks are inconsistent across implementations and there exists no reference architecture (RA) to form a common basis of comparison, evaluation, and integration. To address this gap, we propose an RA of RL frameworks. Through a grounded theory approach, we analyze 18 state-of-the-practice RL frameworks and, by that, we identify recurring architectural components and their relationships, and codify them in an RA. To demonstrate our RA, we reconstruct characteristic RL patterns. Finally, we identify architectural trends, e.g., commonly used components, and outline paths to improving RL frameworks. |
| title | A Reference Architecture of Reinforcement Learning Frameworks |
| topic | Software Engineering Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.06413 |