用于环面码最优纠错的强化学习
量子物理
2020-03-09 v2
摘要
我们应用深度强化学习技术,为无关联噪声下的环面码设计高阈值解码器。仅当解码过程保持环面码的逻辑态时对智能体给予奖励,并在智能体训练阶段使用深度卷积网络,我们观察到在约11%的理论最优阈值附近,对无关联噪声具有近最优性能。我们观察到,总体而言,尽管事先未对任何策略给予偏置,该智能体实施的策略与最小权重完美匹配类似。
引用
@article{arxiv.1911.02308,
title = {Reinforcement learning for optimal error correction of toric codes},
author = {Laia Domingo Colomer and Michalis Skotiniotis and Ramon Muñoz-Tapia},
journal= {arXiv preprint arXiv:1911.02308},
year = {2020}
}
备注
v2: includes more details on teh Reinforcement learning algorithm used as well as the parameters of the neural network, and training phase of the agent