Reinforcement Learning Using Quantum Boltzmann Machines

By Daniel Crawford, Anna Levit, Navid Ghadermarzy, Jaspreet S. Oberoi, & Pooya Ronagh
We investigate whether quantum annealers with select chip layouts can outperform classical computers in reinforcement learning tasks. We associate a transverse fi eld 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 fi rst and last layers of the deep network. In absence of a transverse field, our simulations show that DBMs train more effectively than restricted Boltzmann machines (RBM) with the same number of weights. Since sampling from Boltzmann distributions of a DBM is not classically feasible, this is evidence of advantage of a non-Turing sampling oracle. We then develop a framework for training the network as a quantum Boltzmann machine (QBM) in the presence of a signifi cant transverse field for reinforcement learning. This further improves the reinforcement learning method using DBMs.

Journal reference: D. Crawford, A. Levit, N. Ghadermarzy, J. S. Oberoi, and P. Ronagh, “Reinforcement learning using quantum Boltzmann machines,” Quantum Information and Computation, Volume 18, Issue 1&2, 2018, pp. 0051–0074.
Presented at: Theory of Quantum Computation, Communication and Cryptography TCQ 2017; and Tokyo Institute of Technology, Nanoscience and Quantum Physics Seminar.

PDF     arXiv preprint

Most Recent Papers

Scaling Overhead of Locality Reduction in Binary Optimization Problems

By Elisabetta Valiante, Maritza Hernandez, Amin Barzegar, & Helmut G. Katzgraber Recently, there has been considerable interest in solving optimization problems by mapping these onto a binary representation, sparked mostly by the use of quantum annealing machines....

Quantum Multiple Kernel Learning

By Seyed Shakib Vedaie, Moslem Noori, Jaspreet S. Oberoi, Barry C. Sanders, & Ehsan Zahedinejad Kernel methods play an important role in machine learning applications due to their conceptual simplicity and superior performance on numerous machine learning tasks....