hrvatski jezikClear Cookie - decide language by browser settings

Quantum speedup for active learning agents

Paparo, Giuseppe Davide; Dunjko, Vedran; Makmal, Adi; Martin- Delgado, Miguel Angel; Briegel, Hans J. (2014) Quantum speedup for active learning agents. Physical Review X, 4 . 031002/1-031002/14. ISSN 2160-3308

[img]
Preview
PDF - Published Version - article
Available under License Creative Commons Attribution.

Download (436kB) | Preview

Abstract

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
Uncontrolled Keywords: interdisciplinary physics; quantum physics; quantum information; artificial intelligence
Subjects: TECHNICAL SCIENCES > Computing
Divisions: Division of Molecular Biology
Depositing User: Vedran Dunjko
Date Deposited: 14 Jul 2016 15:02
Last Modified: 14 Jul 2016 15:02
URI: http://fulir.irb.hr/id/eprint/2945
DOI: 10.1103/PhysRevX.4.031002

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year