量子模仿学习
Quantum Imitation Learning
AI总结：
本文提出量子模仿学习（QIL），通过变分量子线路替代DNNs构建Q-BC和Q-GAIL两种算法，在保持与经典方法相当性能的同时有望实现量子加速。
摘要：
尽管在解决各种复杂决策任务中取得了显著成功，但使用深度神经网络（DNNs）训练模仿学习（IL）算法仍面临高昂的计算负担。在本研究中，我们提出了量子模仿学习（QIL），希望利用量子优势加速IL。具体而言，我们开发了两种QIL算法：量子行为克隆（Q-BC）和量子生成对抗模仿学习（Q-GAIL）。Q-BC以负对数似然损失进行离线训练，适用于大量专家数据场景；而Q-GAIL在逆向强化学习框架下工作，采用在线且同策略的方式，适合专家数据有限的场景。对于这两种QIL算法，我们采用变分量子线路（VQCs）替代DNNs来表示策略，并通过数据重上传和缩放参数进行修改，以增强表达能力。我们首先将经典数据编码为量子态作为输入，然后执行VQCs，最后测量量子输出以获得智能体的控制信号。实验结果表明，Q-BC和Q-GAIL均能达到与经典方法相当的性能，并具备量子加速的潜力。据我们所知，我们是首个提出QIL概念并开展初步研究的团队，这为量子时代铺平了道路。
英文摘要：
Despite remarkable successes in solving various complex decision-making tasks, training an imitation learning (IL) algorithm with deep neural networks (DNNs) suffers from the high computation burden. In this work, we propose quantum imitation learning (QIL) with a hope to utilize quantum advantage to speed up IL. Concretely, we develop two QIL algorithms, quantum behavioural cloning (Q-BC) and quantum generative adversarial imitation learning (Q-GAIL). Q-BC is trained with a negative log-likelihood loss in an off-line manner that suits extensive expert data cases, whereas Q-GAIL works in an inverse reinforcement learning scheme, which is on-line and on-policy that is suitable for limited expert data cases. For both QIL algorithms, we adopt variational quantum circuits (VQCs) in place of DNNs for representing policies, which are modified with data re-uploading and scaling parameters to enhance the expressivity. We first encode classical data into quantum states as inputs, then perform VQCs, and finally measure quantum outputs to obtain control signals of agents. Experiment results demonstrate that both Q-BC and Q-GAIL can achieve comparable performance compared to classical counterparts, with the potential of quantum speed-up. To our knowledge, we are the first to propose the concept of QIL and conduct pilot studies, which paves the way for the quantum era.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
