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 annealeru0027s 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. |
Year | Venue | Field |
---|---|---|
2017 | arXiv: Learning | Quantum,Spin-½,Boltzmann machine,Computer science,Quantum computer,Artificial intelligence,Sampling (statistics),Qubit,Machine learning,Reinforcement learning |
DocType | Volume | Citations |
Journal | abs/1706.00074 | 2 |
PageRank | References | Authors |
0.41 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anna Levit | 1 | 2 | 0.41 |
Daniel Crawford | 2 | 2 | 0.41 |
Navid Ghadermarzy | 3 | 10 | 1.94 |
Jaspreet S. Oberoi | 4 | 2 | 0.74 |
Ehsan Zahedinejad | 5 | 7 | 1.60 |
Pooya Ronagh | 6 | 3 | 1.11 |