报告题目：Quantum reinforcement learning

时间：6月8日上午9：00，地点：633会议室

摘要：The key approaches for machine learning, particularly learning in unknown probabilistic environments, are new representations and computation mechanisms. In this paper, a novel quantum reinforcement learning (QRL) method is proposed by combining quantum theory and reinforcement learning (RL). Inspired by the state superposition principle and quantum parallelism, a framework of a value-updating algorithm is introduced. The state (action) in traditional RL is identified as the eigen state (eigen action) in QRL. The state (action) set can be represented with a quantum superposition state, and the eigen state (eigenaction) can be obtained by randomly observing the simulated quantum state according to the collapse postulate of quantum measurement. The probability of the eigen action is determined by the probability amplitude, which is updated in parallel according to rewards. Some related characteristics of QRL such as convergence, optimality, and balancing between exploration and exploitation are also analyzed, which shows that this approach makes a good tradeoff between exploration and exploitation using the probability amplitude and can speedup learning through the quantum parallelism. To evaluate the performance and practicability of QRL, several simulated experiments are given, and the results demonstrate the effectiveness and superiority of the QRL algorithm for some complex problems. This paper is also an effective exploration on the application of quantum computation to artificial intelligence.

简介：董道毅（Daoyi Dong）于1997年进入中国科学技术大学读本科，2006年获博士学位，2006年到中科院数学与系统科学研究院从事博士后研究，随后在浙江大学智能系统与控制研究所担任副教授，现为澳大利亚新南威尔士大学教授。主要研究方向为量子系统控制、量子学习算法。他曾获得中科院院长奖学金、澳大利亚研究理事会（ARC）国家博士后奖励基金、ARC国际合作奖，他与合作者一起获得2014年全球智能控制与自动化世界大会（WCICA）控制理论最佳论文奖,2015年中国控制会议最佳论文奖（关肇直奖），2016年入选澳大利亚新南威尔士大学将改变世界的学术新星。他跟美国普林斯顿大学、华盛顿大学、日本理化研究所、瑞典皇家理工学院、中科院数学与系统科学研究院、南京大学、中国科技大学等单位的合作者有着长期的学术合作。他已在相关领域顶级期刊如IEEE Transactions on Automatic Control、Automatica和国际重要期刊如Scientific Reports, New Journal of Physics, Journal of Chemical Physics等发表期刊论文五十余篇，其中IEEE Transactions和Automatica长文十余篇。担任神经网络顶级期刊IEEE Transactions on Neural Networks and Learning Systems副主编（Associate Editor）。