{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T06:31:26Z","timestamp":1764657086597,"version":"3.46.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T00:00:00Z","timestamp":1756512000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T00:00:00Z","timestamp":1756512000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,30]]},"DOI":"10.1109\/qce65121.2025.00190","type":"proceedings-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T18:22:51Z","timestamp":1764613371000},"page":"1727-1738","source":"Crossref","is-referenced-by-count":0,"title":["Variational Quantum Circuits in Offline Contextual Bandit Problems"],"prefix":"10.1109","author":[{"given":"Lukas","family":"Schulte","sequence":"first","affiliation":[{"name":"Technical University of Munich,Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Hein","sequence":"additional","affiliation":[{"name":"Siemens A G,Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steffen","family":"Udluft","sequence":"additional","affiliation":[{"name":"Siemens A G,Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas A.","family":"Runkler","sequence":"additional","affiliation":[{"name":"Siemens A G,Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2843948"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2514700"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2019.1902"},{"key":"ref5","first-page":"1097","article-title":"Doubly robust policy evaluation and learning","volume-title":"Proceedings of the 28th International Conference on International Conference on Machine Learning, ser. ICML\u201911","author":"Dud\u00edk"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474247"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1103\/physreva.98.032309"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96424-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3010470"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.22331\/q-2022-05-24-720"},{"key":"ref11","article-title":"Quantum embeddings for machine learning","author":"Lloyd","year":"2020","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1103\/physreva.103.032430"},{"key":"ref13","article-title":"Universal approximation of continuous functions with minimal quantum circuits","author":"P\u00e9rez-Salinas","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"1539","article-title":"Practical contextual bandits with regression oracles","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"80","author":"Foster","year":"2018"},{"key":"ref15","article-title":"Offline contextual bandits with high probability fairness guarantees","volume":"32","author":"Metevier","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2021.1193"},{"key":"ref17","first-page":"1049","article-title":"Offline contextual bandits with overparameterized models","volume-title":"International Conference on Machine Learning","author":"Brandfonbrener","year":"2021"},{"key":"ref18","article-title":"Offline neural contextual bandits: Pessimism, optimization and generalization","volume-title":"International Conference on Learning Representations","author":"Nguyen-Tang","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1103\/physrevresearch.2.033125"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.4236\/ns.2019.111003"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.22331\/q-2022-06-29-749"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s42484-020-00024-8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17212"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s42484-024-00189-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ssci.2017.8280935"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-83098-4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.22331\/q-2021-01-28-391"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.22331\/q-2020-02-06-226"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1103\/physrevlett.113.130503"},{"key":"ref30","article-title":"Parametrized quantum policies for reinforcement learning","author":"Jerbi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/nature23879"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/qute.201900070"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5220\/0012348900003636"},{"key":"ref34","article-title":"TensorFlow Quantum: A software framework for quantum machine learning","author":"Broughton","year":"2021","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.09661"},{"volume-title":"TensorFlow: Large-scale machine learning on heterogeneous systems, Software available from tensorflow.org","year":"2015","author":"Abadi","key":"ref36"},{"volume-title":"Keras","year":"2015","author":"Chollet","key":"ref37"},{"key":"ref38","article-title":"PennyLane: Automatic differentiation of hybrid quantum-classical computations","author":"Bergholm","year":"2018","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3460310.3460312"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1137\/040605072"},{"key":"ref41","article-title":"Quantum policy iteration via amplitude estimation and Grover search - towards quantum advantage for reinforcement learning","volume-title":"Transactions on Machine Learning Research","author":"Wiedemann","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08449-y"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08445-2"},{"key":"ref44","article-title":"Roadmap to fault tolerant quantum computation using topological qubit arrays","author":"Aasen","year":"2025","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Quantum Computing and Engineering (QCE)","start":{"date-parts":[[2025,8,30]]},"location":"Albuquerque, NM, USA","end":{"date-parts":[[2025,9,5]]}},"container-title":["2025 IEEE International Conference on Quantum Computing and Engineering (QCE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11249812\/11249813\/11250317.pdf?arnumber=11250317","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T06:28:06Z","timestamp":1764656886000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11250317\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/qce65121.2025.00190","relation":{},"subject":[],"published":{"date-parts":[[2025,8,30]]}}}