AI 中文总结
本文提出一种基于打孔与扩展的极化码设计方法，以RM码为基码，利用强化学习优化扩展比特，显著提升SCLD解码性能。
AI 中文摘要
本文提出了一种新颖的极化码设计方案，采用打孔与扩展技术，旨在提升连续消除列表解码（SCLD）性能。所提出的码设计以称为“基码”的里德-穆勒（RM）码为基础进行。对于基码，首先进行打孔以获得自由度，称为“传输孔”。为此，我们开发了一种打孔方案，以最小化基码最小距离的损失。然后，我们提出了一种新颖的扩展方案，以产生额外的比特，这些比特通过传输孔传输而不产生速率损失。该扩展方案重复基码编码过程中产生的某些编码比特和/或中间比特。重复比特的确定方式是利用强化学习（RL）最大化SCLD性能。此外，我们引入了一种新颖的想法来减少RL的学习空间，这大大加快了扩展比特的设计。虽然所提出的设计方案假设RM码作为基码，但我们表明它可以应用于各种类型的极化码。仿真结果表明，与现有极化码设计相比，采用所提出方案设计的极化码在SCLD性能上有了显著提升。
英文摘要
This work proposes a novel polar code design scheme using puncturing and extending aiming to improve the successive cancellation list decoding (SCLD) performance. The proposed code design is conducted with Reed-Muller (RM) codes called \emph{base} codes. For a base code, puncturing is first performed to gain a degree of freedom, called \emph{transmission holes}. To this end, we develop a puncturing scheme minimizing the loss in the minimum distance of the base code. Then, we propose a novel extending scheme to produce additional bits which are transmitted through the transmission holes without rate loss. The extending scheme repeats some coded bits and/or intermediate bits induced during the encoding of base code. The repeated bits are decided in such a way to maximize the SCLD performance by utilizing reinforcement learning (RL). Moreover, we introduce a novel idea to reduce the learning space of RL, which greatly expedites the design of extended bits. While the proposed design scheme assumes RM codes as base codes, we show that it can be applied to various types of polar code. Simulation results show that the polar codes designed with the proposed scheme have notably improved SCLD performance compared to existing polar code designs.
Comments13 pages, 9 figures
