Continuous Quantum Reinforcement Learning for Robot Navigation

Theodora-Augustina Drăgan, Alexander Künzner, Robert Wille, Jeanette Lorenz

2025

Abstract

One of the multiple facets of quantum reinforcement learning (QRL) is enhancing reinforcement learning (RL) algorithms with quantum submodules, namely with variational quantum circuits (VQC) as function approx-imators. QRL solutions are empirically proven to require fewer training iterations or adjustable parameters than their classical counterparts, but are usually restricted to applications that have a discrete action space and thus limited industrial relevance. We propose a hybrid quantum-classical (HQC) deep deterministic policy gradient (DDPG) approach for a robot to navigate through a maze using continuous states, continuous actions and using local observations from the robot’s LiDAR sensors. We show that this HQC method can lead to models of comparable test results to the neural network (NN)-based DDPG algorithm, that need around 200 times fewer weights. We also study the scalability of our solution with respect to the number of VQC layers and qubits, and find that in general results improve as the layer and qubit counts increase. The best rewards among all similarly sized HQC and classical DDPG methods correspond to a VQC of 8 qubits and 5 layers with no other NN. This work is another step towards continuous QRL, where literature has been sparse.

Paper Citation

in Harvard Style

Drăgan T., Künzner A., Wille R. and Lorenz J. (2025). Continuous Quantum Reinforcement Learning for Robot Navigation. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: QAIO; ISBN 978-989-758-737-5, SciTePress, pages 807-814. DOI: 10.5220/0013371800003890

in Bibtex Style

@conference{qaio25,
author={Theodora-Augustina Drăgan and Alexander Künzner and Robert Wille and Jeanette Lorenz},
title={Continuous Quantum Reinforcement Learning for Robot Navigation},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: QAIO},
year={2025},
pages={807-814},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013371800003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: QAIO
TI - Continuous Quantum Reinforcement Learning for Robot Navigation
SN - 978-989-758-737-5
AU - Drăgan T.
AU - Künzner A.
AU - Wille R.
AU - Lorenz J.
PY - 2025
SP - 807
EP - 814
DO - 10.5220/0013371800003890
PB - SciTePress