This work studies the simplified setting of reinforcement learning with a uniform generative model in which uniformly random state-action samples are available, and provides finite sample guarantees for classical kernelized Fitted Q-Iteration, with classical kernels designed to match the inductive bias of particular parameterized quantum circuits.
Abstract
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.
GRPO-QPS is introduced, a target-preserving framework in which GRPO learns proposal behavior and an exact Metropolis correction preserves the posterior after training, which combines target-preserving Bayesian inference with broad gains over learned transport baselines and a sampling advantage when efficient exploratio...
Yu-Feng Wang, Parivesh Priye, Lu Wei et al.· 0 citations
This work establishes a general quantum score-matching framework with end-to-end theoretical guarantees for quantum states and achieves information-theoretically optimal sample complexity in the high-temperature regime for Hamiltonians with bounded locality and interaction degree.
This paper repurposes uniformly controlled rotations from static state preparation and static data encoding into a state-encoding interface for quantum neural networks, elevating the process of integrating classical states into quantum neural networks to an independent method-ological layer and achieves a more stable p...
Jun-Chen Han, Feng-Tao Xiang, Hao Shi et al.· Chinese Physics B· 0 citations
Variational hybrid quantum models are a common paradigm for realising machine learning on quantum hardware. Nonetheless, they are challenging to train due to several problems intrinsic to the loss landscapes formed by variational quantum circuits. To mitigate these issues, researchers have extended the idea of subspace...
A. R. Barlow, Hans-Martin Rieser, Markus Lange Institute for AI Safety et al.· 0 citations
A reinforcement learning framework that embeds a deterministic Commutation-and-Reduction (CR) algorithm directly into the training environment, enabling the agent to focus its learning capacity on the non-trivial optimizations where reinforcement learning adds real value.
Khoa Dang Tao, Sumin Jin, M. Raza et al.· 0 citations
Numerical results show that the learned architectures recover known benchmark strategies, adapt to dephasing noise, and outperform fixed hardware-efficient ans\"atze while using fewer entangling gates, establishing AutoQSense as a resource-aware approach to adaptive and hardware-compatible quantum sensing.
Jie Liu, Xin Wang· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 28, 2026
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 2, 2026
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
MIT News · Artificial Intelligence· news.mit.eduAug 27, 2026
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.