Preparing stabilizer states via path-aware reinforcement learning

Quantum state preparation forms an essential cornerstone of quantum algorithms.Designing efficient and scalable methods for state preparation on near-term quantum devices remains a significant challenge, with worst-case hardness results compounding this difficulty. We propose a deep reinforcement learning framework for quantum state preparation, using a novel reward function, capable of immediate inference on arbitrary states at a fixed system size post a training phase.This work serves as a starting point for scalable ML-based state preparation algorithms.