Although quantum supremacy is yet to come, there has recently been an increasing interest in identifying the potential of quantum machine learning (QML) in the looming era of practical quantum computing. Motivated by this, in this article we re-design multi-agent reinforcement learning (MARL) based on the unique characteristics of quantum neural networks (QNNs) having two separate dimensions of trainable parameters: angle parameters affecting the output qubit states, and pole parameters associated with the output measurement basis. Exploiting this dyadic trainability as meta-learning capability, we propose quantum meta MARL (QM2ARL) that first applies angle training for meta-QNN learning, followed by pole training for few-shot or local-QNN training. To avoid overfitting, we develop an angle-to-pole regularization technique injecting noise into the pole domain during angle training. Furthermore, by exploiting the pole as the memory address of each trained QNN, we introduce the concept of pole memory allowing one to save and load trained QNNs using only two-parameter pole values. We theoretically prove the convergence of angle training under the angle-to-pole regularization, and by simulation corroborate the effectiveness of QM2ARL in achieving high reward and fast convergence, as well as of the pole memory in fast adaptation to a time-varying environment.
翻译:虽然量子至上尚未到来,但最近人们越来越有兴趣确定量子机器学习(QML)在实际量子计算即将来临的时代中的潜力,为此,我们根据量子神经网络(QNNs)的独特特点,重新设计多剂强化学习(MARL),有两个不同的可训练参数层面:影响输出quit状态的角参数,以及与产出测量基础有关的极参数。将这种可训练性作为元学习能力加以利用,我们提议量子元MARL(QM2ARL)首先为元-QNN学习进行角度培训,然后为少发或本地-QNNN培训进行杆培训。为了避免过度适应,我们在角度训练中将角对球技术的规范化技术注入极域,在角-球级训练中,我们利用极记忆概念概念,允许一个人保存和装载经过训练的QNNM(QM),仅使用两度杆值。我们理论上证明,在角-角-角-角-角-角-级的轨化中,通过快速的模化,使Q-角-角-角-角-轨-级的轨的轨的轨轨轨的轨适应,在快速-级的模拟中,实现快速-级的快速-级-级-级的模拟-级的模拟-级-级-级的模拟-级-级-级-级-级-级-级-级-级-级-级-级-级-级-级-级-级-级-级-级-级-级-级-级-制成成成成成。