Reinforcement learning for optimal error correction of toric codes
Quantum Physics
2020-03-09 v2
Abstract
We apply deep reinforcement learning techniques to design high threshold decoders for the toric code under uncorrelated noise. By rewarding the agent only if the decoding procedure preserves the logical states of the toric code, and using deep convolutional networks for the training phase of the agent, we observe near-optimal performance for uncorrelated noise around the theoretically optimal threshold of 11%. We observe that, by and large, the agent implements a policy similar to that of minimum weight perfect matchings even though no bias towards any policy is given a priori.
Cite
@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}
}
Comments
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