Free energy-based reinforcement learning using a quantum processor

Abstract

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.

Cited by in corpus (8)

• Physics-Inspired Optimization for Quadratic Unconstrained Problems Using a Digital Annealer
• Prospects for Quantum Enhancement with Diabatic Quantum Annealing
• Effective electromagnetic actions for Lorentz violating theories exhibiting the axial anomaly
• Partitioning Dense Graphs with Hardware Accelerators
• Hybrid actor-critic algorithm for quantum reinforcement learning at CERN beam lines
• Feeding the multitude: A polynomial-time algorithm to improve sampling
• Quantum-assisted cluster analysis
• Quantum-assisted finite-element design optimization