Reinforcement Learning Using Quantum Boltzmann Machines
This work addresses the challenge of improving reinforcement learning performance for AI researchers by exploring quantum computing methods, though it is incremental as it builds on existing Boltzmann machine techniques.
The paper tackled the problem of using quantum annealers for reinforcement learning by designing a quantum Boltzmann machine (QBM) framework with simulated quantum annealing, and found that it outperformed classical restricted Boltzmann machines (RBMs) in training effectiveness.
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.