期刊
PHYSICAL REVIEW X
卷 4, 期 3, 页码 -出版社
AMER PHYSICAL SOC
DOI: 10.1103/PhysRevX.4.031002
关键词
-
资金
- Spanish MICINN [FIS2009-10061, FIS2012-33152]
- CAM Research Consortium QUITEMAD [S2009-ESP-1594]
- European Commission PICC [249958]
- UCM-BS [GICC-910758]
- Austrian Science Fund (FWF) [SFB FoQuS F 4012]
- Templeton World Charity Fund [TWCF0078/AB46]
Can quantum mechanics help us build intelligent learning agents? A defining signature of intelligent behavior is the capacity to learn from experience. However, a major bottleneck for agents to learn in real-life situations is the size and complexity of the corresponding task environment. Even in a moderately realistic environment, it may simply take too long to rationally respond to a given situation. If the environment is impatient, allowing only a certain time for a response, an agent may then be unable to cope with the situation and to learn at all. Here, we show that quantum physics can help and provide a quadratic speedup for active learning as a genuine problem of artificial intelligence. This result will be particularly relevant for applications involving complex task environments.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据