Reinforcement Learning for Parameterized Quantum State Preparation: A Comparative Study

• URL: http://arxiv.org/abs/2602.16523v1
• Date: Wed, 18 Feb 2026 15:10:43 GMT
• Title: Reinforcement Learning for Parameterized Quantum State Preparation: A Comparative Study
• Abstract summary: We extend directed quantum circuit synthesis (DQCS) with reinforcement learning from purely discrete gate selection to parameterized quantum state preparation.<n>We compare two training regimes: a one-stage agent that jointly selects the gate type, the affected qubit(s), and the rotation angle.<n>We evaluate Proximal Policy Optimization (PPO) and Advantage Actor--Critic (A2C) on systems comprising two to ten qubits and on targets of increasing complexity.
• Score: 2.4542351340244264
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We extend directed quantum circuit synthesis (DQCS) with reinforcement learning from purely discrete gate selection to parameterized quantum state preparation with continuous single-qubit rotations \(R_x\), \(R_y\), and \(R_z\). We compare two training regimes: a one-stage agent that jointly selects the gate type, the affected qubit(s), and the rotation angle; and a two-stage variant that first proposes a discrete circuit and subsequently optimizes the rotation angles with Adam using parameter-shift gradients. Using Gymnasium and PennyLane, we evaluate Proximal Policy Optimization (PPO) and Advantage Actor--Critic (A2C) on systems comprising two to ten qubits and on targets of increasing complexity with \(λ\) ranging from one to five. Whereas A2C does not learn effective policies in this setting, PPO succeeds under stable hyperparameters (one-stage: learning rate approximately \(5\times10^{-4}\) with a self-fidelity-error threshold of 0.01; two-stage: learning rate approximately \(10^{-4}\)). Both approaches reliably reconstruct computational basis states (between 83\% and 99\% success) and Bell states (between 61\% and 77\% success). However, scalability saturates for \(λ\) of approximately three to four and does not extend to ten-qubit targets even at \(λ=2\). The two-stage method offers only marginal accuracy gains while requiring around three times the runtime. For practicality under a fixed compute budget, we therefore recommend the one-stage PPO policy, provide explicit synthesized circuits, and contrast with a classical variational baseline to outline avenues for improved scalability.

Related papers

• Implicit Differentiation for Measurement-Efficient Bilevel Quantum-Classical Optimization [2.5234274237739402]
  We show how variational quantum algorithms (VQAs) can efficiently handle parametric problems.<n>We propose a bilevel optimization model for diagonal cost Hamiltonians where coefficients depend on a tunable outer parameter.<n>Experiments across three families show that CR-ID consistently improves budget-normalized efficiency by 4% in 1D and over 14% in multi-dimensional settings.
  arXiv  Detail & Related papers  (2026-08-07T19:03:43Z)
• Global Optimization for Parametrized Quantum Circuits [3.558201566667322]
  We study the training of practical classes of quantum circuits with a constant number of trainable parameters.<n>Our main result is a fully randomized approximation scheme (FPRAS)<n>Unlike the standard hybrid quantum-classical training in variational algorithms, our approach separates the computation into two distinct stages.
  arXiv  Detail & Related papers  (2026-03-23T09:49:40Z)
• Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulations [121.39938773554523]
  The Area Under the ROC Curve (AUC) is a pivotal evaluation metric in real-world scenarios with both class imbalance and decision constraints.<n>We present two simple instance-wise minimax reformulations to close the approximation gap of PAUC optimization.<n>The resulting algorithms enjoy a linear per-iteration computational complexity w.r.t. the sample size and a convergence rate of $O(-2/3)$ for typical one-way and two-way PAUCs.
  arXiv  Detail & Related papers  (2025-12-01T02:52:33Z)
• Quantum Phase Classification of Rydberg Atom Systems Using Resource-Efficient Variational Quantum Circuits and Classical Shadows [0.0]
  We present a quantum machine learning approach combining classical shadow tomography with variational quantum circuits.<n>We show that minimal quantum resources suffice for high-accuracy phase classification.<n>This work establishes pathways for quantum-enhanced condensed matter physics on near-term quantum devices.
  arXiv  Detail & Related papers  (2025-10-27T16:25:16Z)
• Pauli Network Circuit Synthesis with Reinforcement Learning [0.0]
  We introduce a Reinforcement Learning-based method for re-synthesis of quantum circuits.<n>We observe average improvements of 20% in two-qubit gate count and depth, reaching up to 60% for many instances.<n>These results highlight the potential of RL-driven synthesis to significantly improve circuit quality in realistic, large-scale quantum transpilation workloads.
  arXiv  Detail & Related papers  (2025-03-18T17:27:50Z)
• ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization [73.60493264901359]
  We present a unified framework for rigorous comparisons across 1-bit, 1.58-bit, 2-bit, 3-bit, and 4-bit quantization settings.<n>We show that ternary, 2-bit, and 3-bit quantization maintains comparable performance in the size-accuracy trade-off.<n>Considering hardware constraints, 2-bit quantization offers promising potential for memory reduction and speedup.
  arXiv  Detail & Related papers  (2025-02-04T18:59:26Z)
• Quantum Gate Generation in Two-Level Open Quantum Systems by Coherent and Incoherent Photons Found with Gradient Search [77.34726150561087]
  We consider an environment formed by incoherent photons as a resource for controlling open quantum systems via an incoherent control. We exploit a coherent control in the Hamiltonian and an incoherent control in the dissipator which induces the time-dependent decoherence rates.
  arXiv  Detail & Related papers  (2023-02-28T07:36:02Z)
• Gradient Estimation with Constant Scaling for Hybrid Quantum Machine Learning [0.0]
  We present a novel method for determining gradients of parameterised quantum circuits (PQCs) in machine learning models. The gradients of PQC layers can be calculated with an overhead of two evaluations per circuit per forward-pass independent of the number of circuit parameters. We find that, as the number of qubits increases, our method converges significantly faster than the parameter shift rule and to a comparable accuracy.
  arXiv  Detail & Related papers  (2022-11-25T09:45:35Z)
• Gradient-descent quantum process tomography by learning Kraus operators [63.69764116066747]
  We perform quantum process tomography (QPT) for both discrete- and continuous-variable quantum systems. We use a constrained gradient-descent (GD) approach on the so-called Stiefel manifold during optimization to obtain the Kraus operators. The GD-QPT matches the performance of both compressed-sensing (CS) and projected least-squares (PLS) QPT in benchmarks with two-qubit random processes.
  arXiv  Detail & Related papers  (2022-08-01T12:48:48Z)
• Unsupervised strategies for identifying optimal parameters in Quantum Approximate Optimization Algorithm [3.508346077709686]
  We study unsupervised Machine Learning approaches for setting parameters without optimization. We showcase them within Recursive-QAOA up to depth $3$ where the number of QAOA parameters used per iteration is limited to $3$. We obtain similar performances to the case where we extensively optimize the angles, hence saving numerous circuit calls.
  arXiv  Detail & Related papers  (2022-02-18T19:55:42Z)
• Optimized fermionic SWAP networks with equivalent circuit averaging for QAOA [2.3362993651992863]
  We optimize the execution of fermionic SWAP networks for Quantum Approximate Optimization Algorithm (QAOA) We introduce Equivalent Circuit Averaging, which randomizes over degrees of freedom in the quantum circuit compilation. We observe a 60% average reduction in error (total variation distance) for QAOA of depth p = 1 on four transmon qubits on a superconducting quantum processor.
  arXiv  Detail & Related papers  (2021-11-08T15:32:05Z)
• Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation [68.25872110275542]
  We propose an efficient inference procedure for non-autoregressive machine translation. It iteratively refines translation purely in the continuous space. We evaluate our approach on WMT'14 En-De, WMT'16 Ro-En and IWSLT'16 De-En.
  arXiv  Detail & Related papers  (2020-09-15T15:30:14Z)
• ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning [91.13797346047984]
  We introduce ADAHESSIAN, a second order optimization algorithm which dynamically incorporates the curvature of the loss function via ADAptive estimates. We show that ADAHESSIAN achieves new state-of-the-art results by a large margin as compared to other adaptive optimization methods.
  arXiv  Detail & Related papers  (2020-06-01T05:00:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.