Adaptive AI for Pulse-Level Quantum Control
Abstract
The Control Variational Quantum Eigensolver (ctrl-VQE) directly optimizes microwave pulses to enable faster and lower-error quantum-state preparation, but its continuous control landscape re- quires efficient search strategies. We demonstrate that a reinforcement-learning agent based on a deep Q learning network can autonomously discover high-performance pulse sequences using only system parameters and a reward function. The approach is fully general for superconducting qubit platforms, requires no ansatz, and operates at nanosecond resolution compatible with hardware con- straints. As a proof of concept, we apply the method to ground-state preparation of the Hydrogen molecule on a simulated superconducting device. The agent consistently identifies optimized control sequences that achieve high fidelity and outperform random-search baselines. These results highlight adaptive learning as a promising hardware-ready framework for pulse-level quantum control.
Related
- Design-Time Conformance Checking for Pulse-Level Quantum Control
- Periodic-Pulse Control of Collective Emission and Photon Statistics in Interacting Quantum Emitters
- Higher-Order Magnus Corrections to Leakage Elimination Operator-Based Quantum Control Pulse Design in the Low-Frequency Regime
- Efficient adaptive control strategy for multi-parameter quantum metrology in two-dimensional systems
- Plasmon-assisted coherent control of a four-level semiconductor quantum dot: operating window and fidelity limits
BibTeX
@misc{shapkota2026adaptive,
title = {{Adaptive AI for Pulse-Level Quantum Control}},
author = {Sanjeev Shapkota and Yayu Mo and Sanjaya Lohani},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.08727},
eprint = {2609.08727},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.08727},
}
RIS
TY - UNPB
TI - Adaptive AI for Pulse-Level Quantum Control
AU - Sanjeev Shapkota
AU - Yayu Mo
AU - Sanjaya Lohani
PY - 2026
DA - 2026/09/08
PB - arXiv
DO - 10.48550/arxiv.2609.08727
UR - https://arxiv.org/abs/2609.08727
AB - The Control Variational Quantum Eigensolver (ctrl-VQE) directly optimizes microwave pulses to enable faster and lower-error quantum-state preparation, but its continuous control landscape re- quires efficient search strategies. We demonstrate that a reinforcement-learning agent based on a deep Q learning network can autonomously discover high-performance pulse sequences using only system parameters and a reward function. The approach is fully general for superconducting qubit platforms, requires no ansatz, and operates at nanosecond resolution compatible with hardware con- straints. As a proof of concept, we apply the method to ground-state preparation of the Hydrogen molecule on a simulated superconducting device. The agent consistently identifies optimized control sequences that achieve high fidelity and outperform random-search baselines. These results highlight adaptive learning as a promising hardware-ready framework for pulse-level quantum control.
ER -