We introduce a classical-quantum hybrid approach to computation, allowing for a quadratic performance improvement in the decision process of a learning agent. Using the paradigm of quantum accelerators, we introduce a routine that runs on a quantum computer, which allows for the encoding of probability distributions. This quantum routine is then employed, in a reinforcement learning set-up, to encode the distributions that drive action choices. Our routine is well-suited in the case of a large, although finite, number of actions and can be employed in any scenario where a probability distribution with a large support is needed. We describe the routine and assess its performance in terms of computational complexity, needed quantum resource, and accuracy. Finally, we design an algorithm showing how to exploit it in the context of Q-learning.

A hybrid classical-quantum approach to speed-up Q-learning

Giordano A;Mastroianni C;
2023

Abstract

We introduce a classical-quantum hybrid approach to computation, allowing for a quadratic performance improvement in the decision process of a learning agent. Using the paradigm of quantum accelerators, we introduce a routine that runs on a quantum computer, which allows for the encoding of probability distributions. This quantum routine is then employed, in a reinforcement learning set-up, to encode the distributions that drive action choices. Our routine is well-suited in the case of a large, although finite, number of actions and can be employed in any scenario where a probability distribution with a large support is needed. We describe the routine and assess its performance in terms of computational complexity, needed quantum resource, and accuracy. Finally, we design an algorithm showing how to exploit it in the context of Q-learning.
2023
Istituto di Calcolo e Reti ad Alte Prestazioni - ICAR
quantum computing
reinforcement learning
File in questo prodotto:
File Dimensione Formato  
s41598-023-30990-5.pdf

accesso aperto

Tipologia: Versione Editoriale (PDF)
Licenza: Dominio pubblico
Dimensione 1.59 MB
Formato Adobe PDF
1.59 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14243/416655
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 6
social impact