基于深度强化学习的置信传播译码算法  

Belief Propagation Decoding Algorithm Based on Deep Reinforcement Learning

作　　者：高源浩 刘乃金[1] 鲁渊明 GAO Yuanhao;LIU Naijin;LU Yuanming(Qian Xuesen Laboratory of Space Technology,China Academy of Space Technology Beijing 100090,China;63893 Troops of PLA,Luoyang 471000,China)

机构地区：[1]中国空间技术研究院钱学森空间技术实验室,北京100090 [2]中国人民解放军63893部队,河南洛阳471000

出　　处：《现代信息科技》2021年第21期98-101,104,共5页Modern Information Technology

摘　　要：文章通过深度强化学习的方法来寻求二进制线性编码的有效解码策略。在加性高斯白噪声的条件下,将置信传播(BP)解码算法中软信息的迭代看作是对软信息的连续决策,并将其映射到马尔可夫决策过程,用深度强化学习网络代替传统译码器,扩大探索空间以提高译码性能,从而实现对数据驱动的最佳决策策略的学习。结果表明,相较于传统BP解码器,在误码率=10;时,学习型BP解码器在BCH码上取得大约0.75 dB的优势,这在一定程度上解决了以往研究中过于依赖数据的问题。This paper uses a deep reinforcement learning approach to find an efficient decoding strategy for binary linear codes.Under the condition of additive Gaussian white noise,the iteration of soft information in the belief propagation (BP) decoding algorithm is regarded as a continuous decision-making of soft information,which is mapped to the Markov decision-making process.The deep reinforcement learning network is used to replace the traditional decoder,expand the exploration space to improve the decoding performance,so as to realize the learning of the best data-driven decision-making strategy.The results show that compared with the traditional BP decoder,when the bit error rate is 10;,the learning BP decoder has an advantage of about 0.75 dB in BCH code,which solves the problem of relying too much on data in previous research to a certain extent.

关 键 词：深度强化学习 置信传播译码 马尔可夫决策 最佳决策 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]