Quantum control of solid state qubits via Reinforcement Learning
Reinforcement learning (RL) was used to design pulse sequences for controlling nitrogen-vacancy (NV) nuclear spins within a spin-bath model of an NV center. The method successfully found high-fidelity state preparation and qubit gate designs, even in the presence of complex, noisy environments. This shows RL can learn robust control strategies for NISQ devices despite modeling uncertainties.