采用分布式优先经验回放的量子深度 Q 学习
Quantum deep Q learning with distributed prioritized experience replay
AI总结:
针对量子强化学习采样复杂度高的问题,提出融合优先经验回放与异步训练的 QDQN-DPER 框架,并通过仿真证明其优于同架构基线。
摘要:
本文提出 QDQN-DPER 框架,以提升量子强化学习(QRL)在求解序列决策任务时的效率。该框架将优先经验回放和异步训练纳入训练算法,以降低较高的采样复杂度。数值仿真表明,QDQN-DPER 的表现优于具有相同模型架构的基线分布式量子 Q 学习方法。所提框架在保持训练效率的同时,具备处理更复杂任务的潜力。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。