Reinforcement Strategy Using Quantum Amplitude Amplification for Robot Learning

作     者：Dong Daoyi1,2,Chen Chunlin3,Li Hanxiong2 1.Key Laboratory of Systems and Control,Institute of Systems Science,Academy of Mathematics and Systems Science,Chinese Academy of Sciences,Beijing 100080,P.R.China2.Department of Manufacturing Engineering and Engineering Management,City University of Hong Kong,Hong Kong,P.R.China.3.Department of Control and Systems Engineering,Nanjing University,Nanjing 210093,P.R.China 

会议名称：《第二十六届中国控制会议》

会议日期：2007年

学科分类：07[理学] 080202[工学-机械电子工程] 08[工学] 0804[工学-仪器科学与技术] 0802[工学-机械工程] 070201[理学-理论物理] 081201[工学-计算机系统结构] 0702[理学-物理学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the China Postdoctoral Science Founda-tion under Grant 20060400515 a grant from RGC of Hong Kong(CityU:116905) 

关 键 词：Reinforcement Learning Quantum Amplitude Amplification Robot Learning Reinforcement Strategy 

摘      要：Quantum amplitude amplification is a kind of useful technique in quantum computation and it can boost the success probability of some quantum *** strategy in reinforcement learning is essentially to boost the selection probability of good *** the common characteristics,this paper uses the idea of amplitude amplification to reinforcement learning as a new reinforcement strategy,proposes a learning algorithm based on quantum amplitude amplification and demonstrates its effectiveness through simulated experiments.