A Reinforcement Learning Based Universal Sequence Design for Polar Codes
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918310492241920 |
|---|---|
| author | Ho, David Kin Wai Fazeli, Arman Mansour, Mohamad M. Jalloul, Louay M. A. |
| author_facet | Ho, David Kin Wai Fazeli, Arman Mansour, Mohamad M. Jalloul, Louay M. A. |
| contents | To advance Polar code design for 6G applications, we develop a reinforcement learning-based universal sequence design framework that is extensible and adaptable to diverse channel conditions and decoding strategies. Crucially, our method scales to code lengths up to $2048$, making it suitable for use in standardization. Across all $(N,K)$ configurations supported in 5G, our approach achieves competitive performance relative to the NR sequence adopted in 5G and yields up to a 0.2 dB gain over the beta-expansion baseline at $N=2048$. We further highlight the key elements that enabled learning at scale: (i) incorporation of physical law constrained learning grounded in the universal partial order property of Polar codes, (ii) exploitation of the weak long term influence of decisions to limit lookahead evaluation, and (iii) joint multi-configuration optimization to increase learning efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20118 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Reinforcement Learning Based Universal Sequence Design for Polar Codes Ho, David Kin Wai Fazeli, Arman Mansour, Mohamad M. Jalloul, Louay M. A. Machine Learning To advance Polar code design for 6G applications, we develop a reinforcement learning-based universal sequence design framework that is extensible and adaptable to diverse channel conditions and decoding strategies. Crucially, our method scales to code lengths up to $2048$, making it suitable for use in standardization. Across all $(N,K)$ configurations supported in 5G, our approach achieves competitive performance relative to the NR sequence adopted in 5G and yields up to a 0.2 dB gain over the beta-expansion baseline at $N=2048$. We further highlight the key elements that enabled learning at scale: (i) incorporation of physical law constrained learning grounded in the universal partial order property of Polar codes, (ii) exploitation of the weak long term influence of decisions to limit lookahead evaluation, and (iii) joint multi-configuration optimization to increase learning efficiency. |
| title | A Reinforcement Learning Based Universal Sequence Design for Polar Codes |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.20118 |