To define a quantum error correction code, first one needs to model noise, such as Pauli noise, dephasing noise, etc.

Then according to the noise, look for the code space, stabilizer, and logical operators.

The whole process is really hard and the performance of defined codes may not be that good.

So I want to know if there is any machine learning method for finding quantum error correction codes. Given the settings of our noise, the algorithm searches for a good QEC code automatically with a high distance and $p_{th}$, and low consumed physical qubits.

  • $\begingroup$ Such a things doesn't exist for classical codes...if it did it would put a lot of people out of work. So don't expect much for quantum codes. $\endgroup$
    – unknown
    Commented Jun 10 at 2:39
  • $\begingroup$ We've been collecting references here: errorcorrectionzoo.org/c/reinforcement_learning $\endgroup$ Commented Jul 2 at 14:24

1 Answer 1


At least in this paper, they use reinforcement learning for optimizing QEC codes. Though, they constrain the search to a family of surface codes.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.