Quantum Policy Gradient Algorithm with Optimized Action Decoding
Meyer N, Scherer DD, Plinge A, Mutschler C, Hartmann M (2023)
Publication Type: Conference contribution
Publication year: 2023
Publisher: ML Research Press
Book Volume: 202
Pages Range: 24592-24613
Conference Proceedings Title: Proceedings of Machine Learning Research
Event location: Honolulu, HI
Abstract
Quantum machine learning implemented by variational quantum circuits (VQCs) is considered a promising concept for the noisy intermediate-scale quantum computing era. Focusing on applications in quantum reinforcement learning, we propose an action decoding procedure for a quantum policy gradient approach. We introduce a quality measure that enables us to optimize the classical post-processing required for action selection, inspired by local and global quantum measurements. The resulting algorithm demonstrates a significant performance improvement in several benchmark environments. With this technique, we successfully execute a full training routine on a 5-qubit hardware device. Our method introduces only negligible classical overhead and has the potential to improve VQC-based algorithms beyond the field of quantum reinforcement learning.
Authors with CRIS profile
Additional Organisation(s)
Involved external institutions
Germany (DE)How to cite
APA:
Meyer, N., Scherer, D.D., Plinge, A., Mutschler, C., & Hartmann, M. (2023). Quantum Policy Gradient Algorithm with Optimized Action Decoding. In Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett (Eds.), Proceedings of Machine Learning Research (pp. 24592-24613). Honolulu, HI, US: ML Research Press.
MLA:
Meyer, Nico, et al. "Quantum Policy Gradient Algorithm with Optimized Action Decoding." Proceedings of the 40th International Conference on Machine Learning, ICML 2023, Honolulu, HI Ed. Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett, ML Research Press, 2023. 24592-24613.
BibTeX: Download