A hybrid classical-quantum approach to speed-up Q-learning
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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-30990-5 |
| _version_ | 1797865002422501376 |
|---|---|
| author | A. Sannia A. Giordano N. Lo Gullo C. Mastroianni F. Plastina |
| author_facet | A. Sannia A. Giordano N. Lo Gullo C. Mastroianni F. Plastina |
| author_sort | A. Sannia |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-09T23:01:02Z |
| format | Article |
| id | doaj.art-b0231e7c71094539a47f03395d2880d8 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T23:01:02Z |
| publishDate | 2023-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-b0231e7c71094539a47f03395d2880d82023-03-22T10:59:20ZengNature PortfolioScientific Reports2045-23222023-03-0113111010.1038/s41598-023-30990-5A hybrid classical-quantum approach to speed-up Q-learningA. Sannia0A. Giordano1N. Lo Gullo2C. Mastroianni3F. Plastina4Dipartimento di Fisica, Università della CalabriaICAR-CNRDipartimento di Fisica, Università della CalabriaICAR-CNRDipartimento di Fisica, Università della CalabriaAbstract 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.https://doi.org/10.1038/s41598-023-30990-5 |
| spellingShingle | A. Sannia A. Giordano N. Lo Gullo C. Mastroianni F. Plastina A hybrid classical-quantum approach to speed-up Q-learning Scientific Reports |
| title | A hybrid classical-quantum approach to speed-up Q-learning |
| title_full | A hybrid classical-quantum approach to speed-up Q-learning |
| title_fullStr | A hybrid classical-quantum approach to speed-up Q-learning |
| title_full_unstemmed | A hybrid classical-quantum approach to speed-up Q-learning |
| title_short | A hybrid classical-quantum approach to speed-up Q-learning |
| title_sort | hybrid classical quantum approach to speed up q learning |
| url | https://doi.org/10.1038/s41598-023-30990-5 |
| work_keys_str_mv | AT asannia ahybridclassicalquantumapproachtospeedupqlearning AT agiordano ahybridclassicalquantumapproachtospeedupqlearning AT nlogullo ahybridclassicalquantumapproachtospeedupqlearning AT cmastroianni ahybridclassicalquantumapproachtospeedupqlearning AT fplastina ahybridclassicalquantumapproachtospeedupqlearning AT asannia hybridclassicalquantumapproachtospeedupqlearning AT agiordano hybridclassicalquantumapproachtospeedupqlearning AT nlogullo hybridclassicalquantumapproachtospeedupqlearning AT cmastroianni hybridclassicalquantumapproachtospeedupqlearning AT fplastina hybridclassicalquantumapproachtospeedupqlearning |