{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T16:46:21Z","timestamp":1768409181874,"version":"3.49.0"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Quantum Eng."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tqe.2024.3418094","type":"journal-article","created":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T17:33:51Z","timestamp":1719250431000},"page":"1-11","source":"Crossref","is-referenced-by-count":3,"title":["On Quantum Natural Policy Gradients"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6659-9277","authenticated-orcid":false,"given":"Andr\u00e9","family":"Sequeira","sequence":"first","affiliation":[{"name":"Department of Informatics, University of Minho, Braga, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4466-1129","authenticated-orcid":false,"given":"Luis Paulo","family":"Santos","sequence":"additional","affiliation":[{"name":"Department of Informatics, University of Minho, Braga, Portugal"}]},{"given":"Luis Soares","family":"Barbosa","sequence":"additional","affiliation":[{"name":"Department of Informatics, University of Minho, Braga, Portugal"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1109\/TNN.1998.712192","volume-title":"Reinforcement Learning - An Introduction","author":"Sutton","year":"1998"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.10.003"},{"key":"ref3","volume-title":"Artificial Intelligence: A Modern Approach","author":"Russell","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2017.2743240"},{"key":"ref5","first-page":"1531","article-title":"A natural policy gradient","volume-title":"Advances in Neural Information Processing Systems","volume":"14","author":"Kakade","year":"2001"},{"key":"ref6","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Advances in Neural Information Processing Systems","volume":"12","author":"Sutton","year":"1999"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"issue":"1","key":"ref8","first-page":"98:4431","article-title":"On the theory of policy gradient methods: Optimality, approximation, and distribution shift","volume":"22","author":"Agarwal","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref10","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.22331\/q-2022-05-24-720"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3010470"},{"key":"ref13","first-page":"24592","article-title":"Quantum policy gradient algorithm with optimized action decoding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Meyer","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s42484-023-00101-8"},{"key":"ref15","first-page":"28362","article-title":"Parametrized quantum policies for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Jerbi","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.22331\/q-2023-11-29-1191"},{"key":"ref17","article-title":"Quantum policy gradient algorithms","author":"Jerbi","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/qce57702.2023.10181"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.22331\/q-2020-05-25-269"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.22331\/q-2021-09-09-539"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41534-019-0141-3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.99.032331"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-83098-4"},{"key":"ref24","article-title":"Optimal training of variational quantum algorithms without barren plateaus","author":"Haug","year":"2021"},{"key":"ref25","volume-title":"Matrix Analysis (ser. Graduate Texts in Mathematics)","volume":"169","author":"Bhatia","year":"1997"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45421-2_1"},{"key":"ref27","article-title":"PennyLane: Automatic differentiation of hybrid quantum-classical computations","author":"Bergholm","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.4.013083"}],"container-title":["IEEE Transactions on Quantum Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8924785\/10379182\/10569042.pdf?arnumber=10569042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T19:11:52Z","timestamp":1738005112000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10569042\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/tqe.2024.3418094","relation":{},"ISSN":["2689-1808"],"issn-type":[{"value":"2689-1808","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}