Reinforcement Learning for Syndrome Extraction
Abstract
A key subtask of quantum error correction is to extract a syndrome that, if nontrivial, signals an error. The number of possible ways to extract a syndrome grows exponentially with the syndrome size, and these implementations vary greatly in fault tolerance, as measured by their logical error rates. This creates a natural search problem: find an implementation with a low logical error rate. Previous work solves this problem but sacrifices either solution quality or scalability. In this paper, we use reinforcement learning and importance sampling to outperform previous work at all scales. Compared with the state of the art automatic scheduling tools AlphaSyndrome and PropHunt, our tool reduces the logical error rate by 25.9\% and 71.7\% on average, respectively, culminating with a reduction of 97.8\% for a surface code with distance 15.
Related
- Transversal syndrome extraction: A unifying construction for measuring the error syndromes of any stabilizer code
- Coherent errors, syndrome extraction and the Robustness of Magic in stabiliser codes
- The Intrinsic Cost of Quantum Syndrome Extraction
- Reinforcement learning for robust calibration of multiqudit quantum gates
- Discovering network resilience formulas with symbolized reinforcement learning
BibTeX
@misc{ye2026reinforcement,
title = {{Reinforcement Learning for Syndrome Extraction}},
author = {John Zhuoyang Ye and Aarav Pabla and Jens Palsberg},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.12020},
eprint = {2609.12020},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.12020},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Reinforcement Learning for Syndrome Extraction
AU - John Zhuoyang Ye
AU - Aarav Pabla
AU - Jens Palsberg
PY - 2026
DA - 2026/09/10
PB - arXiv
DO - 10.48550/arxiv.2609.12020
UR - https://arxiv.org/abs/2609.12020
AB - A key subtask of quantum error correction is to extract a syndrome that, if nontrivial, signals an error. The number of possible ways to extract a syndrome grows exponentially with the syndrome size, and these implementations vary greatly in fault tolerance, as measured by their logical error rates. This creates a natural search problem: find an implementation with a low logical error rate. Previous work solves this problem but sacrifices either solution quality or scalability. In this paper, we use reinforcement learning and importance sampling to outperform previous work at all scales. Compared with the state of the art automatic scheduling tools AlphaSyndrome and PropHunt, our tool reduces the logical error rate by 25.9\% and 71.7\% on average, respectively, culminating with a reduction of 97.8\% for a surface code with distance 15.
ER -