Optimizing Quantum Error Correction Codes with Reinforcement Learning
Problem
Determining the most suited quantum error correction encoding for unknown error channels or specific laboratory setups is highly challenging.
Why it matters
Quantum error correction is widely thought to be the key to fault-tolerant quantum computation.
What the AI did
A reinforcement learning agent modifies surface-code quantum memories until a desired logical error rate is reached, finding near-optimal configurations and transferring learned experience to different settings.
Results
Near-optimal solutions in number of data qubits for various error models, demonstrated in simulations with about 70 data qubits; transfer across settings shown.
Impact
Evidence supports RL finding near-optimal QEC code configurations in simulation; laboratory validation not claimed.
Record
| Venue | Quantum |
|---|---|
| Published | 2019 |
| Work type | article |
| Authors | Hendrik Poulsen Nautrup, Nicolas Delfosse, Vedran Dunjko, Hans J. Briegel, Nicolai Friis |
| Citations | 158 (OpenAlex, at import time) |
| References | 74 |
| Model or method | reinforcement learning agent (specific algorithm not stated) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.22331/q-2019-12-16-215 |
| Open access | gold |
| Keywords | quantum error correction, reinforcement learning, surface code, transfer learning, fault tolerance |
Importance rating
significant — thousands to millions affected
Abstract states QEC is widely thought to be the key to fault-tolerant quantum computation, a foundational scientific goal; RL finds near-optimal code configurations, though only in simulation.
More in Physics & Astronomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Magnetic control of tokamak plasmas through deep reinforcement learning | 2022 | 739 |
7
|
| 2 | Solving the quantum many-body problem with artificial neural networks | 2017 | 2,205 |
7
|
| 3 | Learning high-accuracy error decoding for quantum processors | 2024 | 90 |
7
|
| 4 | Machine-learning-assisted correction of correlated qubit errors in a topological code | 2018 | 141 |
7
|
| 5 | Quantum Error Correction with Quantum Autoencoders | 2023 | 36 |
7
|