Reinforcement Learning vs. Gradient-Based Optimisation for Robust Energy Landscape Control of Spin-1/2 Quantum Networks
arXiv:2109.07226 · doi:10.1109/CDC45484.2021.9683463
Abstract
We explore the use of policy gradient methods in reinforcement learning for quantum control via energy landscape shaping of XX-Heisenberg spin chains in a model agnostic fashion. Their performance is compared to finding controllers using gradient-based L-BFGS optimisation with restarts, with full access to an analytical model. Hamiltonian noise and coarse-graining of fidelity measurements are considered. Reinforcement learning is able to tackle challenging, noisy quantum control problems where L-BFGS optimization algorithms struggle to perform well. Robustness analysis under different levels of Hamiltonian noise indicates that controllers found by reinforcement learning appear to be less affected by noise than those found with L-BFGS.
arXiv comment7 pages, 7 figures
References in corpus (17)
- Continuous control with deep reinforcement learning
- Quantum Computing in the NISQ era and beyond
- A variational eigenvalue solver on a quantum processor
- Trust Region Policy Optimization
- Addressing Function Approximation Error in Actor-Critic Methods
- Coupling Superconducting Qubits via a Cavity Bus
- Training Schrödinger's cat: quantum optimal control
- Quantum control theory and applications: A survey
- Quantum information processing with superconducting qubits in a microwave field
- Reinforcement Learning in Different Phases of Quantum Control
- Fidelity-based Probabilistic Q-learning for Control of Quantum Systems
- Learning Robust and High-Precision Quantum Controls
- Global optimization of quantum dynamics with AlphaZero deep exploration
- Sampling-based Learning Control for Quantum Systems with Uncertainties
- Symmetry & Controllability for Spin Networks with a Single-Node Control
- Design of Feedback Control Laws for Information Transfer in Spintronics Networks
- Time optimal information transfer in spintronics networks