Adaptive Reinforcement Learning for Robust Open Quantum System Control: A Multi-Task Framework with Temporal Optimization

2026-05-26

AI Summary

This work addresses the challenge of achieving high-fidelity and robust quantum state transfer in noisy open quantum systems governed by multiple Hamiltonians. The authors propose a multi-task Soft Actor-Critic reinforcement learning framework that, for the first time, integrates multi-task learning with adaptive optimization of both the evolution time \(T\) and the number of pulse segments \(N\) for open-system control. The method demonstrates efficient generalization across 51 Hamiltonian variants and significantly outperforms the GRAPE benchmark. Its superior robustness under pulse perturbations and varying decoherence conditions is quantitatively validated using a newly introduced Robustness-induced Infidelity Metric (RIM), establishing a novel paradigm for universal quantum control.

Abstract

We present a Multi-task Soft Actor-Critic (SAC) Reinforcement Learning framework designed for open-system quantum control across diverse Hamiltonians, which learns optimal pulse sequences while simultaneously discovering problem-specific evolution time T and number of control pulse segments N. Experimental results across 51 Hamiltonian variations demonstrate that the multi-task SAC model is able to generate control pulses that can drive a system, under environment noise, from its initial state to its target state with high fidelities, establishing essential foundations for universal quantum control applicable to realistic noisy quantum devices. Through progressive expansion of the training Hamiltonian set, we investigate if a single multi-task model trained using a given number of sample Hamiltonians can successfully accomplish state-transfer tasks for Hamiltonians drawn from the same Hamiltonian space but not encountered during training. In addition, our Robustness Infidelity Measure (RIM) analysis reveals that SAC trained policies exhibit superior robustness to pulse amplitude perturbations and decoherence rate variations compared to GRAPE-optimized controls.

Problem

• open quantum system
• robust control
• quantum state transfer
• Hamiltonian generalization
• noise resilience

Innovation

• Multi-task Reinforcement Learning
• Soft Actor-Critic
• Open Quantum System Control
• Robustness Infidelity Measure
• Temporal Optimization