Quantum speedup for active learning agents



Downloads per month over past year

Davide Paparo, Giuseppe and Dunjko, Vedran and Makmal, Adi and Martín-Delgado Alcántara, Miguel Ángel and Briegel, Hans J. (2014) Quantum speedup for active learning agents. Physical review X, 4 (3). ISSN 2160-3308

[thumbnail of Martín Delgado Alcántara MÁ 05 LIBRE.pdf]

Official URL: http://dx.doi.org/10.1103/PhysRevX.4.031002


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 reallife 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.

Item Type:Article
Additional Information:

©2014 American Physical Society. M. A. M.-D. acknowledges support by the Spanish MICINN Grants No. FIS2009-10061 and No. FIS2012- 33152, the CAM Research Consortium QUITEMAD S2009-ESP-1594, the European Commission PICC: FP7 2007-2013, Grant No. 249958, and the UCM-BS Grant No. GICC-910758. H. J. B. acknowledges support by the Austrian Science Fund (FWF) through the SFB FoQuS F 4012, and the Templeton World Charity Fund grant TWCF0078/AB46. G. D. P. and V. D. have contributed equally to this work.

Uncontrolled Keywords:Computation; Algorithms; Network; Google.
Subjects:Sciences > Physics > Physics-Mathematical models
ID Code:47323
Deposited On:04 May 2018 09:55
Last Modified:04 May 2018 17:32

Origin of downloads

Repository Staff Only: item control page