Prospects of reinforcement learning for the simultaneous damping of many mechanical modes

Abstract

We apply adaptive feedback for the partial refrigeration of a mechanical resonator, i.e. with the aim to simultaneously cool the classical thermal motion of more than one vibrational degree of freedom. The feedback is obtained from a neural network parametrized policy trained via a reinforcement learning strategy to choose the correct sequence of actions from a finite set in order to simultaneously reduce the energy of many modes of vibration. The actions are realized either as optical modulations of the spring constants in the so-called quadratic optomechanical coupling regime or as radiation pressure induced momentum kicks in the linear coupling regime. As a proof of principle we numerically illustrate efficient simultaneous cooling of four independent modes with an overall strong reduction of the total system temperature.

arXiv commentMachine learning in Optomechanics: cooling

References in corpus (40)

• Cavity Optomechanics
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Sideband Cooling Micromechanical Motion to the Quantum Ground State
• Machine learning phases of matter
• Strong dispersive coupling of a high finesse cavity to a micromechanical membrane
• Quantum Theory of Cavity-Assisted Sideband Cooling of Mechanical Motion
• Theory of ground state cooling of a mechanical oscillator using dynamical back-action
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• Self-cooling of a micro-mirror by radiation pressure
• Learning phase transitions by confusion
• Ground-state cooling of a micromechanical oscillator: generalized framework for cold damping and cavity-assisted cooling schemes
• Cooling of a mirror by radiation pressure
• Measurement-based quantum control of mechanical motion
• Dispersive optomechanics: a membrane inside a cavity
• Feedback cooling of a cantilever's fundamental mode below 5 mK
• Machine learning quantum phases of matter beyond the fermion sign problem
• Parametric Oscillatory Instability in Fabry-Perot (FP) Interferometer
• Optomechanical Cooling of a Macroscopic Oscillator by Homodyne Feedback
• Measurement and control of a mechanical oscillator at its thermal decoherence rate
• Cavity cooling of an optically levitated nanoparticle
• Reinforcement Learning in Different Phases of Quantum Control
• Active learning machine learns to create new quantum experiments
• Cavity cooling a single charged nanoparticle
• Sideband Cooling Beyond the Quantum Limit with Squeezed Light
• Reinforcement Learning with Neural Networks for Quantum Feedback
• Feedback cooling of a single trapped ion
• Deep learning and the Schrödinger equation
• Cold Damping of an Optically Levitated Nanoparticle to micro-Kelvin Temperatures
• The Optimal Reward Baseline for Gradient-Based Reinforcement Learning
• Cavity cooling of a levitated nanosphere by coherent scattering
• Fidelity-based Probabilistic Q-learning for Control of Quantum Systems
• Cavity cooling of free silicon nanoparticles in high-vacuum
• Cavity-Based 3D Cooling of a Levitated Nanoparticle via Coherent Scattering
• Robust stationary mechanical squeezing in a kicked quadratic optomechanical system
• Enhancing sideband cooling by feedback--controlled light
• Two-membrane cavity optomechanics
• Partial Optomechanical Refrigeration via Multimode Cold-Damping Feedback
• Quantum enhanced feedback cooling of a mechanical oscillator
• A controllable two-membrane-in-the-middle cavity optomechanical system
• Quantum feedback cooling of a single trapped ion in front of a mirror

Cited by in corpus (5)

• Cavity-Based 3D Cooling of a Levitated Nanoparticle via Coherent Scattering
• Deep Reinforcement Learning for Quantum State Preparation with Weak Nonlinear Measurements
• Multimode cold-damping optomechanics with delayed feedback
• Accurate phonon blockade detector composed of a quadratically coupled optomechanical system
• The Quantum Cartpole: A benchmark environment for non-linear reinforcement learning