REINFORCEMENT LEARNING USING QUANTUM BOLTZMANN MACHINES

作     者：Crawford, Daniel Levit, Anna Ghadermarzy, Navid Oberoi, Jaspreet S. Ronaghe, Pooya 

作者机构：1QB Informat Technol 1QBit Vancouver BC Canada Univ British Columbia Dept Math Vancouver BC Canada Simon Fraser Univ Sch Engn Sci Burnaby BC Canada Univ Waterloo Inst Quantum Comp Waterloo ON Canada Univ Waterloo Dept Phys & Astron Waterloo ON Canada 

出 版 物：《QUANTUM INFORMATION & COMPUTATION》 (Quantum Inf. Comput.)

年 卷 期：2018年第18卷第1-2期

页      面：51-74页

核心收录：

学科分类：07[理学] 070201[理学-理论物理] 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：We would like to thank Hamed Karimi  Helmut Katzgraber  Murray Thom  Matthias Troyer  and Ehsan Zahedinejad  as well as the referees and editorial board of Quantum Information and Computation  for reviewing this work and providing many helpful suggestions. The idea of using SQA to run experiments involving measurements with a nonzero transverse field was communicated in person by Mohammad Amin. We would also like to thank Marko Bucyk for editing this manuscript 

主　　题：Reinforcement learning Machine learning Neuro-dynamic programming Markov decision process Quantum Monte Carlo simulation Simulated quantum annealing Restricted Boltzmann machine Deep Boltzmann machine General Boltzmann machine Quantum Boltzmann machine 

摘      要：We investigate whether quantum annealers with select chip layouts can outperform classical computers in reinforcement learning tasks. We associate a transverse field Ising spin Hamiltonian with a layout of qubits similar to that of a deep Boltzmann machine (DBM) and use simulated quantum annealing (SQA) to numerically simulate quantum sampling from this system. We design a reinforcement learning algorithm in which the set of visible nodes representing the states and actions of an optimal policy are the first and last layers of the deep network. In absence of a transverse field, our simulations show that DBMs are trained more effectively than restricted Boltzmann machines (RBM) with the same number of nodes. We then develop a framework for training the network as a quantum Boltzmann machine (QBM) in the presence of a significant transverse field for reinforcement learning. This method also outperforms the reinforcement learning method that uses RBMs.