Reinforcement Learning for Bit-Flipping Decoding of Polar Codes
A traditional successive cancellation (SC) decoding algorithm produces error propagation in the decoding process. In order to improve the SC decoding performance, it is important to solve the error propagation. In this paper, we propose a new algorithm combining reinforcement learning and SC flip (S...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/2/171 |
| _version_ | 1797405820169748480 |
|---|---|
| author | Xiumin Wang Jinlong He Jun Li Liang Shan |
| author_facet | Xiumin Wang Jinlong He Jun Li Liang Shan |
| author_sort | Xiumin Wang |
| collection | DOAJ |
| description | A traditional successive cancellation (SC) decoding algorithm produces error propagation in the decoding process. In order to improve the SC decoding performance, it is important to solve the error propagation. In this paper, we propose a new algorithm combining reinforcement learning and SC flip (SCF) decoding of polar codes, which is called a Q-learning-assisted SCF (QLSCF) decoding algorithm. The proposed QLSCF decoding algorithm uses reinforcement learning technology to select candidate bits for the SC flipping decoding. We establish a reinforcement learning model for selecting candidate bits, and the agent selects candidate bits to decode the information sequence. In our scheme, the decoding delay caused by the metric ordering can be removed during the decoding process. Simulation results demonstrate that the decoding delay of the proposed algorithm is reduced compared with the SCF decoding algorithm, based on critical set without loss of performance. |
| first_indexed | 2024-03-09T03:16:44Z |
| format | Article |
| id | doaj.art-31e212ac6ef64aefbcc0660b8791dcdb |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-09T03:16:44Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-31e212ac6ef64aefbcc0660b8791dcdb2023-12-03T15:18:04ZengMDPI AGEntropy1099-43002021-01-0123217110.3390/e23020171Reinforcement Learning for Bit-Flipping Decoding of Polar CodesXiumin Wang0Jinlong He1Jun Li2Liang Shan3Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou 310018, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou 310018, ChinaBinjiang College, Nanjing University of Information Science and Technology, Wuxi 214105, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou 310018, ChinaA traditional successive cancellation (SC) decoding algorithm produces error propagation in the decoding process. In order to improve the SC decoding performance, it is important to solve the error propagation. In this paper, we propose a new algorithm combining reinforcement learning and SC flip (SCF) decoding of polar codes, which is called a Q-learning-assisted SCF (QLSCF) decoding algorithm. The proposed QLSCF decoding algorithm uses reinforcement learning technology to select candidate bits for the SC flipping decoding. We establish a reinforcement learning model for selecting candidate bits, and the agent selects candidate bits to decode the information sequence. In our scheme, the decoding delay caused by the metric ordering can be removed during the decoding process. Simulation results demonstrate that the decoding delay of the proposed algorithm is reduced compared with the SCF decoding algorithm, based on critical set without loss of performance.https://www.mdpi.com/1099-4300/23/2/171polar codesreinforcement learningsuccessive cancellationbit-flipping decodingQ-learning-assisted decoding |
| spellingShingle | Xiumin Wang Jinlong He Jun Li Liang Shan Reinforcement Learning for Bit-Flipping Decoding of Polar Codes Entropy polar codes reinforcement learning successive cancellation bit-flipping decoding Q-learning-assisted decoding |
| title | Reinforcement Learning for Bit-Flipping Decoding of Polar Codes |
| title_full | Reinforcement Learning for Bit-Flipping Decoding of Polar Codes |
| title_fullStr | Reinforcement Learning for Bit-Flipping Decoding of Polar Codes |
| title_full_unstemmed | Reinforcement Learning for Bit-Flipping Decoding of Polar Codes |
| title_short | Reinforcement Learning for Bit-Flipping Decoding of Polar Codes |
| title_sort | reinforcement learning for bit flipping decoding of polar codes |
| topic | polar codes reinforcement learning successive cancellation bit-flipping decoding Q-learning-assisted decoding |
| url | https://www.mdpi.com/1099-4300/23/2/171 |
| work_keys_str_mv | AT xiuminwang reinforcementlearningforbitflippingdecodingofpolarcodes AT jinlonghe reinforcementlearningforbitflippingdecodingofpolarcodes AT junli reinforcementlearningforbitflippingdecodingofpolarcodes AT liangshan reinforcementlearningforbitflippingdecodingofpolarcodes |