arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.05577quant-phcs.AIcs.LGstat.ML
收藏

用于强化学习的参数化量子策略

Parametrized quantum policies for reinforcement learning

Sofiene Jerbi, Casper Gyurik, Simon C. Marshall, Hans J. Briegel, Vedran Dunjko

摘要:

随着现实世界量子计算的出现,参数化量子计算可以用作量子经典机器学习系统中的假设族的想法正在获得越来越多的关注。这种混合系统已经显示出在监督和生成学习中解决现实世界任务的潜力,最近的工作已经在特殊的人工任务中建立了可证明的优势。然而,在强化学习的情况下,这可以说是最具挑战性的,学习的提升将是非常有价值的,没有任何建议已经成功地解决了标准的基准测试任务,也没有显示出理论学习优于经典算法。在这项工作中,我们实现了两者。我们提出了一个使用很少量子位的混合量子-经典强化学习模型,我们证明它可以有效地训练来解决几个标准的基准测试环境。此外,我们展示并正式证明了参数化量子线路解决某些学习任务的能力,这些任务对于经典模型来说是难以解决的,包括当前最先进的深度神经网络,在离散对数问题的经典难度下。

英文摘要:

With the advent of real-world quantum computing, the idea that parametrized quantum computations can be used as hypothesis families in a quantum-classical machine learning system is gaining increasing traction. Such hybrid systems have already shown the potential to tackle real-world tasks in supervised and generative learning, and recent works have established their provable advantages in special artificial tasks. Yet, in the case of reinforcement learning, which is arguably most challenging and where learning boosts would be extremely valuable, no proposal has been successful in solving even standard benchmarking tasks, nor in showing a theoretical learning advantage over classical algorithms. In this work, we achieve both. We propose a hybrid quantum-classical reinforcement learning model using very few qubits, which we show can be effectively trained to solve several standard benchmarking environments. Moreover, we demonstrate, and formally prove, the ability of parametrized quantum circuits to solve certain learning tasks that are intractable for classical models, including current state-of-art deep neural networks, under the widely-believed classical hardness of the discrete logarithm problem.

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。

↑