Deep Reinforcement Learning Control of Quantum Cartpoles

Code

• github.com/Z-T-WANG/DeepReinforcementLearningControlOfQuantumCartpoles
  OfficialIn paperpytorch★ 10

Abstract

We generalize a standard benchmark of reinforcement learning, the classical cartpole balancing problem, to the quantum regime by stabilizing a particle in an unstable potential through measurement and feedback. We use state-of-the-art deep reinforcement learning to stabilize a quantum cartpole and find that our deep learning approach performs comparably to or better than other strategies in standard control theory. Our approach also applies to measurement-feedback cooling of quantum oscillators, showing the applicability of deep learning to general continuous-space quantum control.

Tasks

Reproductions