Free energy-based reinforcement learning using a quantum processor
This work addresses the challenge of leveraging quantum sampling for reinforcement learning, but it is incremental as it builds on existing quantum hardware and theoretical frameworks.
The authors tackled the problem of applying quantum hardware to reinforcement learning by introducing free energy-based reinforcement learning (FERL) and using a quantum annealer to approximate free energy in a quantum Boltzmann machine, with experimental results on a grid-world problem showing it as a promising method.
Recent theoretical and experimental results suggest the possibility of using current and near-future quantum hardware in challenging sampling tasks. In this paper, we introduce free energy-based reinforcement learning (FERL) as an application of quantum hardware. We propose a method for processing a quantum annealer's measured qubit spin configurations in approximating the free energy of a quantum Boltzmann machine (QBM). We then apply this method to perform reinforcement learning on the grid-world problem using the D-Wave 2000Q quantum annealer. The experimental results show that our technique is a promising method for harnessing the power of quantum sampling in reinforcement learning tasks.