Variational quantum algorithms represent a promising approach to quantum machine learning where classical neural networks are replaced by parametrized quantum circuits. Here, we present a variational approach to quantize projective simulation (PS), a reinforcement learning model aimed at interpretable artificial intelligence. Decision making in PS is modeled as a random walk on a graph describing the agent's memory. To implement the quantized model, we consider quantum walks of single photons in a lattice of tunable Mach-Zehnder interferometers. We propose variational algorithms tailored to reinforcement learning tasks, and we show, using an example from transfer learning, that the quantized PS learning model can outperform its classical counterpart. Finally, we discuss the role of quantum interference for training and decision making, paving the way for realizations of interpretable quantum learning agents.

翻译：变分量子算法通过可参数化的量子电路替代经典神经网络，为量子机器学习展现了一种极具前景的途径。本文提出了一种量化投影模拟（PS）的变分方法——该投影模拟是一种旨在实现可解释人工智能的强化学习模型。在PS中，决策过程被建模为描述智能体记忆的图结构上的随机游走。为实现该量化模型，我们考虑在可调谐马赫-曾德尔干涉仪构成的晶格中进行单光子量子游走。我们提出了专为强化学习任务定制的变分算法，并通过迁移学习实例证明，量化PS学习模型的性能可超越其经典对应模型。最后，我们探讨了量子干涉对训练与决策制定的作用，为可解释量子学习智能体的实现铺平了道路。