PreprintCC BY 4.0arXiv
Quantum Hierarchical Reinforcement Learning via Variational Quantum Circuits
Abstract
While parameterized quantum computations have shown success in standard reinforcement learning (RL), whether these advantages adapt to hierarchical RL (HRL) remains a critical open question. This work demonstrates that variational quantum circuits (VQCs) can effectively enhance HRL agents based on the option-critic architecture. Evaluated in standard environments, a hybrid HRL agent with a quantum feature extractor outperforms classical baselines while using fewer parameters. We also identify an architectural bottleneck: using VQCs for option-value estimation severely degrades learning. Further ablations reveal how quantum circuit design affects performance. Our work establishes design principles for parameter-efficient hybrid HRL agents.
Related
- Operator Learning with Variational Quantum Circuits
- Classical State Preparation for Variational Quantum Algorithms via Reinforcement Learning
- Hierarchical Fourier Approximation for Variational Quantum Distribution Learning
- BAHAMAS: A Control Plane for Optimization and Execution of Variational Quantum Circuits
- Subspace Controllability in Variational Quantum Circuits: Maximising Expressivity and Increasing Search Efficiency with Dynamical Lie Algebras
BibTeX
@misc{lee2026quantum,
title = {{Quantum Hierarchical Reinforcement Learning via Variational Quantum Circuits}},
author = {Yu-Ting Lee and Samuel Yen-Chi Chen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2605.03434},
eprint = {2605.03434},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.03434},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Quantum Hierarchical Reinforcement Learning via Variational Quantum Circuits
AU - Yu-Ting Lee
AU - Samuel Yen-Chi Chen
PY - 2026
DA - 2026/09/19
PB - arXiv
DO - 10.48550/arxiv.2605.03434
UR - https://arxiv.org/abs/2605.03434
AB - While parameterized quantum computations have shown success in standard reinforcement learning (RL), whether these advantages adapt to hierarchical RL (HRL) remains a critical open question. This work demonstrates that variational quantum circuits (VQCs) can effectively enhance HRL agents based on the option-critic architecture. Evaluated in standard environments, a hybrid HRL agent with a quantum feature extractor outperforms classical baselines while using fewer parameters. We also identify an architectural bottleneck: using VQCs for option-value estimation severely degrades learning. Further ablations reveal how quantum circuit design affects performance. Our work establishes design principles for parameter-efficient hybrid HRL agents.
ER -