Reinforcement learning using quantum Boltzmann machines  (pp0051-0074)
          Daniel Crawford, Anna Levit, Navid Ghadermarzy, Jaspreet S. Oberoi, and Pooya Ronagh
          doi: https://doi.org/10.26421/QIC18.1-2-3
Abstracts: 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.
Key words: 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 Communicated by: S Braunstein & A Harr