Meyer N, Murauer J, Popov A, Ufrecht C, Plinge A, Mutschler C, Scherer DD (2024)
Publication Type: Conference contribution
Publication year: 2024
Publisher: Institute of Electrical and Electronics Engineers Inc.
Book Volume: 1
Pages Range: 1458-1466
Conference Proceedings Title: Proceedings - IEEE Quantum Week 2024, QCE 2024
Event location: Montreal, QC, CAN
ISBN: 9798331541378
DOI: 10.1109/QCE60285.2024.00172
Reinforcement learning is a powerful framework aiming to determine optimal behavior in highly complex decision-making scenarios. This objective can be achieved using policy iteration, which requires to solve a typically large linear system of equations. We propose the variational quantum policy iteration (VarQPI) algorithm, realizing this step with a NISQ-compatible quantum-enhanced subroutine. Its scalability is supported by an analysis of the structure of generic reinforcement learning environments' laying the foundation for potential quantum advantage with utility-scale quantum computers. Furthermore, we introduce the warm-start initialization variant (WS-VarQPI) that significantly reduces resource overhead. The algorithm solves a large FrozenLake environment with an underlying 256×256-dimensional linear system, indicating its practical robustness.
APA:
Meyer, N., Murauer, J., Popov, A., Ufrecht, C., Plinge, A., Mutschler, C., & Scherer, D.D. (2024). Warm-Start Variational Quantum Policy Iteration. In Candace Culhane, Greg T. Byrd, Hausi Muller, Yuri Alexeev, Yuri Alexeev, Sarah Sheldon (Eds.), Proceedings - IEEE Quantum Week 2024, QCE 2024 (pp. 1458-1466). Montreal, QC, CAN: Institute of Electrical and Electronics Engineers Inc..
MLA:
Meyer, Nico, et al. "Warm-Start Variational Quantum Policy Iteration." Proceedings of the 5th IEEE International Conference on Quantum Computing and Engineering, QCE 2024, Montreal, QC, CAN Ed. Candace Culhane, Greg T. Byrd, Hausi Muller, Yuri Alexeev, Yuri Alexeev, Sarah Sheldon, Institute of Electrical and Electronics Engineers Inc., 2024. 1458-1466.
BibTeX: Download