arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.00686cs.LGphysics.opticsquant-ph
收藏

物理强化学习分层结构中的单光子:光子智能

Single photon in hierarchical architecture for physical reinforcement learning: Photon intelligence

Network System Research Institute, National Institute of Information and Communications Technology(情报通信研究机构网络系统研究所);CNRS, Inst. NEEL(法国国家科学研究中心奈尔研究所);Université Grenoble Alpes, Inst. NEEL(格勒诺布尔-阿尔卑斯大学奈尔研究所);Interdisciplinary Graduate School of Medicine and Engineering, University of Yamanashi(山梨大学医学与工学跨学科研究生院);WPI Center for Materials Nanoarchitectonics, National Institute for Materials Science(国立材料科学研究所WPI材料纳米结构学中心)

Makoto Naruse, Martin Berthel, Aurélien Drezet, Serge Huant, Hirokazu Hori, Song-Ju Kim

摘要:

理解和使用自然过程的智能功能,称为自然智能,最近吸引了来自各个领域的兴趣,包括后硅计算的人工智能和决策的行为科学。在过去的研究中,我们成功地利用单光子的波粒二象性解决了双臂强盗问题,这构成了强化学习和决策的基础。在这项研究中,我们提出并确认了基于单光子的强化学习和决策的分层架构,验证了该原则的可扩展性。具体而言,四臂强盗问题解决了零先验知识的两层分层架构,其中偏振是自主适应,以实现充分的决策,使用单光子测量。在分层结构中,出现了层依赖决策的概念。然而,粗层和细层的最优解在某些矛盾问题上是相互冲突的。我们发现,虽然我们所谓的锦标赛策略解决了这样的矛盾,单光子的概率性质允许直接定位的最优解,即使是矛盾的问题,从而体现了单光子的探索能力。这项研究为未来人工智能的分层结构中的光子智能以及智能功能的自然过程的潜力提供了见解。

英文摘要:

Understanding and using natural processes for intelligent functionalities, referred to as natural intelligence, has recently attracted interest from a variety of fields, including post-silicon computing for artificial intelligence and decision making in the behavioural sciences. In a past study, we successfully used the wave-particle duality of single photons to solve the two-armed bandit problem, which constitutes the foundation of reinforcement learning and decision making. In this study, we propose and confirm a hierarchical architecture for single-photon-based reinforcement learning and decision making that verifies the scalability of the principle. Specifically, the four-armed bandit problem is solved given zero prior knowledge in a two-layer hierarchical architecture, where polarization is autonomously adapted in order to effect adequate decision making using single-photon measurements. In the hierarchical structure, the notion of layer-dependent decisions emerges. The optimal solutions in the coarse layer and in the fine layer, however, conflict with each other in some contradictive problems. We show that while what we call a tournament strategy resolves such contradictions, the probabilistic nature of single photons allows for the direct location of the optimal solution even for contradictive problems, hence manifesting the exploration ability of single photons. This study provides insights into photon intelligence in hierarchical architectures for future artificial intelligence as well as the potential of natural processes for intelligent functionalities.

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。

↑