Metraipolis › archive › dc_1001805461e2

Towards Surrogate Based Dequantization of Quantum Reinforcement Learning — arXiv:2609.16266

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16266
License (as archived)
CC0-1.0
Archived
2026-10-15T22:05:23.586Z
SHA-256 of the archived text
734fe567db3010d38fd2ca2b8b6e777dbd1a72fb82fa84d026be4e9d9a7a0da0
Stable URL of this page
https://metraipolis.com/documento/dc_1001805461e2

How to cite

Towards Surrogate Based Dequantization of Quantum Reinforcement Learning — arXiv:2609.16266 — arXiv (en), https://arxiv.org/abs/2609.16266 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1001805461e2 (Metraipolis archive dc_1001805461e2, sha256 734fe567db3010d38fd2ca2b8b6e777dbd1a72fb82fa84d026be4e9d9a7a0da0)
BibTeX
@misc{dc1001805461e2,
  title = {Towards Surrogate Based Dequantization of Quantum Reinforcement Learning — arXiv:2609.16266},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16266},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1001805461e2; sha256 734fe567db3010d38fd2ca2b8b6e777dbd1a72fb82fa84d026be4e9d9a7a0da0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16266. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In recent years, the utility of parameterized quantum circuits as function approximators has been widely studied. In the context of reinforcement learning, this approach has led to variational quantum algorithms such as quantum Q-learning. While these methods show promising empirical results, and can provide provable advantages for artificial problems, it remains unclear whether they can provide a provable quantum advantage over classical approaches for problems of practical relevance. A natural way to investigate this question is through the lens of dequantization: The construction of efficient classical algorithms capable of matching the performance of quantum variational methods. Building on recent kernel-based dequantization results for supervised learning, we take steps towards extending this surrogate-based dequantization program to reinforcement learning. Specifically, we study the simplified setting of reinforcement learning with a uniform generative model in which uniformly random state-action samples are available, which models the regime of sampling from a large experience replay buffer after sufficient exploration. Within this setting, we provide finite sample guarantees for classical kernelized Fitted Q-Iteration, with classical kernels designed to match the inductive bias of particular parameterized quantum circuits. Using these results, we then provide a set of sufficient conditions, on the data-encoding strategy of a parameterized quantum circuit, the corresponding classical kernel, and the problem structure, under which kernelized Fitted Q-Iteration provides a meaningful dequantization of quantum Q-learning, in this simplified setting. Apart from providing rigorous dequantization guarantees when these conditions are met, these results also motivate the use of kernelized fitted Q-iteration as a dequantization heuristic when these sufficient conditions cannot be verified.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-09-16 in quant-ph).
Categorie arXiv: Quantum Physics (quant-ph) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.16266 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T21:52:12.785Z dalla pagina https://arxiv.org/catchup/quant-ph/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).