Quantum deep Q learning with distributed prioritized experience replay

TL;DR

This paper presents QDQN-DPER, a framework that improves quantum reinforcement learning efficiency by integrating prioritized experience replay and asynchronous training, showing superior performance over baseline methods.

Contribution

The paper introduces a novel QDQN-DPER framework that combines prioritized experience replay with distributed quantum deep Q-learning, enhancing training efficiency and scalability.

Findings

QDQN-DPER outperforms baseline distributed quantum Q-learning.

The framework reduces sampling complexity in quantum RL.

Potential for tackling more complex tasks while maintaining efficiency.

Abstract

This paper introduces the QDQN-DPER framework to enhance the efficiency of quantum reinforcement learning (QRL) in solving sequential decision tasks. The framework incorporates prioritized experience replay and asynchronous training into the training algorithm to reduce the high sampling complexities. Numerical simulations demonstrate that QDQN-DPER outperforms the baseline distributed quantum Q learning with the same model architecture. The proposed framework holds potential for more complex tasks while maintaining training efficiency.