Deep Reinforcement Learning for Individual Atomic Control and Cooling

• URL: http://arxiv.org/abs/2606.30765v1
• Date: Mon, 29 Jun 2026 18:01:40 GMT
• Title: Deep Reinforcement Learning for Individual Atomic Control and Cooling
• Abstract summary: Real-time feedback control of quantum systems is often limited by partial observations, nonlinear dynamics and measurement noise.<n>We show that deep reinforcement learning can cool the motion of a single neutral atom coupled to a high-finesse optical cavity.
• Score: 4.9577109795938865
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-time feedback control of quantum systems is often limited by partial observations, nonlinear dynamics and measurement noise, which make accurate model-based controllers difficult to design. Here we show that deep reinforcement learning can cool the motion of a single neutral atom coupled to a high-finesse optical cavity using only the continuously monitored cavity transmission. We first train the controller in simulation and then transfer it to the experiment, where online fine-tuning adapts it to unmodeled experimental dynamics. The learned policy damps the atom's motion in real time and achieves a cooling time constant of 388 +/- 14 microseconds, corresponding to only two motional periods in the trap. It also outperforms a standard linear differentiator controller in cooling speed while maintaining comparable atom retention over a broad range of operating conditions. These results establish reinforcement learning as a practical strategy for feedback control in quantum-limited experiments where compact analytical models are incomplete.

Related papers

• End-to-End Learning of Quantum Control on Latent Dynamical Manifold [13.119254069186034]
  Traditional quantum control relies on an iterative "simulate-then-optimize" paradigm.<n>We propose an end-to-end quantum control framework based on long short-term memory.
  arXiv  Detail & Related papers  (2026-06-26T09:57:12Z)
• Learning Minimal Representations of Many-Body Physics from Snapshots of a Quantum Simulator [0.08796261172196741]
  We develop a machine learning approach based on a variational autoencoder (VAE) to analyze interference measurements of Bose gases.<n>Applying to non-equilibrium protocols, the latent space uncovers signatures of frozen-in solitons following rapid cooling.<n>Results demonstrate that generative models can extract physically interpretable variables directly from noisy and sparse experimental data.
  arXiv  Detail & Related papers  (2025-09-17T08:38:46Z)
• Forecasting Continuous Non-Conservative Dynamical Systems in SO(3) [51.510040541600176]
  We propose a novel approach to modeling the rotation of moving objects in computer vision.<n>Our approach is agnostic to energy and momentum conservation while being robust to input noise.<n>By learning to approximate object dynamics from noisy states during training, our model attains robust extrapolation capabilities in simulation and various real-world settings.
  arXiv  Detail & Related papers  (2025-08-11T09:03:10Z)
• Constructive interference at the edge of quantum ergodic dynamics [116.94795372054381]
  We characterize ergodic dynamics using the second-order out-of-time-order correlators, OTOC$(2)$.<n>In contrast to dynamics without time reversal, OTOC$(2)$ are observed to remain sensitive to the underlying dynamics at long time scales.
  arXiv  Detail & Related papers  (2025-06-11T21:29:23Z)
• Multi-mode cooling of a Bose-Einstein condensate with linear quantum feedback [0.0]
  We theoretically investigate measurement-based feedback control over the motional degrees of freedom of an oblate quasi-2D atomic Bose-Einstein condensate (BEC)<n>We develop a linear-quadratic-Gaussian (LQG) model that describes the multi-mode dynamics of the condensate's collective excitations under continuous measurement and control.<n>We present analytical results showing that collective excitations can be cooled to below single-phonon average occupation.
  arXiv  Detail & Related papers  (2025-06-03T02:26:48Z)
• Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Time [57.30651532625017]
  We present a novel hybrid method that integrates numerical simulation, neural physics, and generative control.<n>Our system demonstrates robust performance across diverse 2D/3D scenarios, material types, and obstacle interactions.<n>We promise to release both models and data upon acceptance.
  arXiv  Detail & Related papers  (2025-05-25T01:27:18Z)
• Quantum emulation of the transient dynamics in the multistate Landau-Zener model [50.591267188664666]
  We study the transient dynamics in the multistate Landau-Zener model as a function of the Landau-Zener velocity. Our experiments pave the way for more complex simulations with qubits coupled to an engineered bosonic mode spectrum.
  arXiv  Detail & Related papers  (2022-11-26T15:04:11Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)
• Real-time optimal quantum control of mechanical motion at room temperature [4.050112001048099]
  We show real-time optimal control of the quantum trajectory of an optically trapped nanoparticles. In combination with levitation, this paves the way to full-scale control over the wavepacket dynamics of macroscopic quantum objects.
  arXiv  Detail & Related papers  (2020-12-30T15:14:11Z)
• Fast and differentiable simulation of driven quantum systems [58.720142291102135]
  We introduce a semi-analytic method based on the Dyson expansion that allows us to time-evolve driven quantum systems much faster than standard numerical methods. We show results of the optimization of a two-qubit gate using transmon qubits in the circuit QED architecture.
  arXiv  Detail & Related papers  (2020-12-16T21:43:38Z)
• Generation and storage of spin squeezing via learning-assisted optimal control [7.460567829296081]
  We consider a collective spin system coupled to a bosonic field, and show that proper constant-value controls in this model can simulate the dynamical behaviors of these two models. A better performance of squeezing can be obtained when the control is time-varying, which is generated via a reinforcement learning algorithm. We propose a four-step strategy for the construction of a new type of combined controls, which include both constant-value and time-varying controls, but performed at different time intervals.
  arXiv  Detail & Related papers  (2020-10-26T09:31:04Z)

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.