We provide the ultimate precision attainable in spectroscopy of a quantum emitter using single-photon pulses. We find that the maximum precision of linewidth estimation is independent of the details of the emitter's bare Hamiltonian, though this is not true for the detunings. We also identify optimal pulse shapes attaining these precisions.

arXiv:2510.08386Physical Review AFeb 24, 20261 citation

Superconducting quantum computing optimization based on multi-objective deep reinforcement learning

Yangting Liu

Scientific ReportsJan 30, 20257 citations

International Conference on Information Networking

Deep Reinforcement Learning for Optimal Pulse Shaping in Single-Photon Quantum Emitters

Syed Muhammad Abuzar Rizvi, Jae Uk Roh, Hyundong Shin

Published Jan 14, 2026• 0 citations

Publisher

DOI: 10.1109/icoin68469.2026.11480491

Related papers

Reinforcement Learning for Quantum Control

Barry C. Sanders, Pantita Palittapongarnpim, Seyed Shakib Vedaie

Bulletin of the American Physical SocietyMar 7, 20180 citations

Deep Reinforcement Learning Quantum Control on IBMQ Platforms and Qiskit Pulse

Rudy Semola, Lorenzo Del Moro, Davide Bacciu +1 more

Quantum optimal control theory (QOCT) typically addresses the control of physical qubits. Finding explicit pulse control sequences in such a framework is challenging, especially when an underlying physical model is unknown. We propose a deep reinforcement learning (DRL) method, which doesn't require any underlying gate model or qubit pre-calibration, capable of controlling a superconductive qubit via analog pulses acting in the IBM Qiskit Pulse environment. We applied the method to build a single-qubit gate with high fidelity and short duration at pulse level. In particular, the DRL agent approximated the X90 gate at the physical layer on the IBM Armonk transmon superconductive qubit simulated by the Qiskit Pulse simulator. The learned sequence has an average gate fidelity greater than 0.978 and a duration of 58 ns only, faster than the default X90 pulse IBM implementation, which has a runtime of 140 ns. Without prior knowledge and gate model knowledge, the agent learned a non-traditional shaped microwave pulse, providing an alternative strategy for controlling noisy quantum states.Quantum optimal control theory (QOCT) typically addresses the control of physical qubits. Finding explicit pulse control sequences in such a framework is challenging, especially when an underlying physical model is unknown. We propose a deep reinforcement learning (DRL) method, which doesn't require any underlying gate model or qubit pre-calibration, capable of controlling a superconductive qubit via analog pulses acting in the IBM Qiskit Pulse environment. We applied the method to build a single-qubit gate with high fidelity and short duration at pulse level. In particular, the DRL agent approximated the X90 gate at the physical layer on the IBM Armonk transmon superconductive qubit simulated by the Qiskit Pulse simulator. The learned sequence has an average gate fidelity greater than 0.978 and a duration of 58 ns only, faster than the default X90 pulse IBM implementation, which has a runtime of 140 ns. Without prior knowledge and gate model knowledge, the agent learned a non-traditional shaped microwave pulse, providing an alternative strategy for controlling noisy quantum states.

IEEE International Conference on Quantum Computing and Engineering (QCE)Sep 1, 20224 citations

Optimising Quantum Gate Fidelity with Deep Reinforcement Learning

Leander Grech, Gianluca Valentino, Simon Hirländer

Jan 1, 20240 citations

Discovering autonomous quantum error correction via deep reinforcement learning

Yue Yin, Tailong Xiao, Xiaoyang Deng +3 more

Quantum error correction is essential for fault-tolerant quantum computing. However, standard methods relying on active measurements may introduce additional errors. Autonomous quantum error correction (AQEC) circumvents this by utilizing engineered dissipation and drives in bosonic systems, but identifying practical encoding remains challenging due to stringent Knill-Laflamme conditions. In this work, we utilize curriculum learning enabled deep reinforcement learning to discover Bosonic codes under approximate AQEC framework to resist both single-photon and double-photon losses. We present an analytical solution of solving the master equation under approximation conditions, which can significantly accelerate the training process of reinforcement learning. The agent first identifies an encoded subspace surpassing the breakeven point through rapid exploration within a constrained evolutionary time-frame, then strategically fine-tunes its policy to sustain this performance advantage over extended temporal horizons. We find that the two-phase trained agent can discover the optimal set of codewords, i.e., the Fock states $\ket{4}$ and $\ket{7}$ considering the effect of both single-photon and double-photon loss. We identify that the discovered code surpasses the breakeven threshold over a longer evolution time and achieve the state-of-art performance. We also analyze the robustness of the code against the phase damping and amplitude damping noise. Our work highlights the potential of curriculum learning enabled deep reinforcement learning in discovering the optimal quantum error correct code especially in early fault-tolerant quantum systems.Quantum error correction is essential for fault-tolerant quantum computing. However, standard methods relying on active measurements may introduce additional errors. Autonomous quantum error correction (AQEC) circumvents this by utilizing engineered dissipation and drives in bosonic systems, but identifying practical encoding remains challenging due to stringent Knill-Laflamme conditions. In this work, we utilize curriculum learning enabled deep reinforcement learning to discover Bosonic codes under approximate AQEC framework to resist both single-photon and double-photon losses. We present an analytical solution of solving the master equation under approximation conditions, which can significantly accelerate the training process of reinforcement learning. The agent first identifies an encoded subspace surpassing the breakeven point through rapid exploration within a constrained evolutionary time-frame, then strategically fine-tunes its policy to sustain this performance advantage over extended temporal horizons. We find that the two-phase trained agent can discover the optimal set of codewords, i.e., the Fock states $\ket{4}$ and $\ket{7}$ considering the effect of both single-photon and double-photon loss. We identify that the discovered code surpasses the breakeven threshold over a longer evolution time and achieve the state-of-art performance. We also analyze the robustness of the code against the phase damping and amplitude damping noise. Our work highlights the potential of curriculum learning enabled deep reinforcement learning in discovering the optimal quantum error correct code especially in early fault-tolerant quantum systems.

quant-pharXiv:2511.12482Physical Review ANov 18, 20250 citations

Optimal quantum spectroscopy using single-photon pulses

Sourav Das, Aiman Khan, Francesco Albarelli +1 more

arXiv:2510.08386Physical Review AFeb 24, 20261 citation

Superconducting quantum computing optimization based on multi-objective deep reinforcement learning

Yangting Liu

Deep reinforcement learning is considered an effective technology in quantum optimization and can provide strategies for optimal control of complex quantum systems. More precise measurements require simulation control at multiple experimental stages. Based on this, we improved a multi-objective deep reinforcement learning method in mathematical convex optimization theory for multi-process quantum optimal control optimization. By setting the single-process quantum control optimization result as a multi-objective optimization truncation threshold and reward function transfer strategy, we finally gave a global optimal solution that considers multiple influencing factors, rather than a local optimal solution that only targets a certain error. This method achieved excellent computational results on superconducting qubits. Optimum control of multi-process quantum computing can be achieved only by regulating the microwave pulse parameters of superconducting qubits, and such a set of global parameter values and control strategies are given.Deep reinforcement learning is considered an effective technology in quantum optimization and can provide strategies for optimal control of complex quantum systems. More precise measurements require simulation control at multiple experimental stages. Based on this, we improved a multi-objective deep reinforcement learning method in mathematical convex optimization theory for multi-process quantum optimal control optimization. By setting the single-process quantum control optimization result as a multi-objective optimization truncation threshold and reward function transfer strategy, we finally gave a global optimal solution that considers multiple influencing factors, rather than a local optimal solution that only targets a certain error. This method achieved excellent computational results on superconducting qubits. Optimum control of multi-process quantum computing can be achieved only by regulating the microwave pulse parameters of superconducting qubits, and such a set of global parameter values and control strategies are given.

Scientific ReportsJan 30, 20257 citations

\ket{4}

and

\ket{7}

considering the effect of both single-photon and double-photon loss. We identify that the discovered code surpasses the breakeven threshold over a longer evolution time and achieve the state-of-art performance. We also analyze the robustness of the code against the phase damping and amplitude damping noise. Our work highlights the potential of curriculum learning enabled deep reinforcement learning in discovering the optimal quantum error correct code especially in early fault-tolerant quantum systems.