Quantum reinforcement learning

doi:10.1109/TSMCB.2008.925743

CSpace

	Quantum reinforcement learning
	Dong, Daoyi 1; Chen, Chunlin 2; Li, Hanxiong 3,4; Tarn, Tzyh-Jong 5
	2008-10-01
发表期刊	IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS
ISSN	1083-4419
卷号	38 期号:5 页码:1207-1220
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 (eigen action) 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.
关键词	collapse Grover iteration probability amplitude quantum reinforcement learning (QRL) state superposition
DOI	10.1109/TSMCB.2008.925743
语种	英语
资助项目	National Natural Science Foundation of China[60703083] ; K. C. Wong Education Foundation (Hong Kong) ; China Postdoctoral Science Foundation[20060400515] ; RGC of Hong Kong[CityU:116406]
WOS研究方向	Automation & Control Systems ; Computer Science
WOS类目	Automation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000259191900003
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/5603
专题	中国科学院数学与系统科学研究院
通讯作者	Dong, Daoyi
作者单位	1.Chinese Acad Sci, Key Lab Syst & Control, Inst Syst Sci, Acad Math & Syst Sci, Beijing 100190, Peoples R China 2.Nanjing Univ, Dept Control & Syst Engn, Nanjing 210093, Peoples R China 3.Cent S Univ, Changsha 410083, Peoples R China 4.City Univ Hong Kong, Dept Mfg Engn & Engn Management, Kowloon, Hong Kong, Peoples R China 5.Washington Univ, Dept Elect & Syst Engn, St Louis, MO 63130 USA
推荐引用方式 GB/T 7714	Dong, Daoyi,Chen, Chunlin,Li, Hanxiong,et al. Quantum reinforcement learning[J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS,2008,38(5):1207-1220.
APA	Dong, Daoyi,Chen, Chunlin,Li, Hanxiong,&Tarn, Tzyh-Jong.(2008).Quantum reinforcement learning.IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS,38(5),1207-1220.
MLA	Dong, Daoyi,et al."Quantum reinforcement learning".IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 38.5(2008):1207-1220.