{
  "abstract": "Training quantum neural networks (QNNs) on near-term hardware remains hampered by two compounding difficulties: the exponential vanishing of gradient variance known as the barren plateau, and the $\\mathcal{O}(L \\cdot 2^n)$ time and memory cost of differentiating through an $n$-qubit, $L$-layer circuit. We propose RLQ-Grad, a reinforcement-learning-based optimizer in which a classical policy $π_ϕ$ (a spectrally-normalized PPO agent) learns to propose parameter updates directly, conditioned on the QNN's current parameters, loss, accuracy, and previous update. Because the surrogate gradient is emitted by a classical network rather than obtained by differentiating through the unitary $U(θ)$, its variance is not constrained by the barren plateau concentration bound, and its cost scales with the number of trainable parameters rather than the Hilbert-space dimension. We prove these properties formally and verify them on a hardware-efficient ansatz across four supervised benchmarks with up to $n=20$ qubits. RLQ-Grad preserves a near-flat gradient-variance curve where backpropagation, parameter-shift, and adjoint differentiation decay by 1 to 2 orders of magnitude. Accounting for the full training pipeline (PPO rollouts, actor-critic updates, and optimizer states), RLQ-Grad needs under 2 MB of memory and runs $2490\\times$, $7876\\times$, and $673\\times$ faster per iteration than these three methods at $n=20$. It improves top-1 accuracy by up to $+10\\%$ over gradient-based baselines on circuits of up to 12 qubits, and matches dedicated barren plateau mitigation methods on CIFAR-10 at 14 to 20 qubits, where evolutionary and gradient-free optimizers collapse to chance.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.31066",
  "author_total": 4,
  "authors": [
    {
      "name": "Nhan Trong Luu"
    },
    {
      "name": "Duong Trung Luu"
    },
    {
      "name": "Nam Ngoc Pham"
    },
    {
      "name": "Thang Cong Truong"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5jjz0n2sgt8fy.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.31066",
  "fulltext_url": null,
  "id": "5jjz0n2sgt8fy",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.31066",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.ET"
    ],
    [
      "arxiv",
      "cs.NE"
    ],
    [
      "arxiv",
      "quant-ph"
    ],
    [
      "openalex",
      "1702|Quantum Computing Algorithms and Architecture"
    ]
  ],
  "openalex": "W7214624573",
  "pdf_url": "https://arxiv.org/pdf/2609.31066",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-25",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/5jjz0n2sgt8fy.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:52Z",
      "native_id": "2609.31066",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.31066"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "Modeling quantum neural network gradient with reinforcement learning",
  "title_text": "Modeling quantum neural network gradient with reinforcement learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:52Z",
  "url": "https://research.draconitic.com/paper/5jjz0n2sgt8fy",
  "venue": "arXiv",
  "versions": []
}