{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T05:10:05Z","timestamp":1746594605641,"version":"3.40.5"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Research Ireland","award":["18\/CRT\/6183"],"award-info":[{"award-number":["18\/CRT\/6183"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3564392","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T17:41:22Z","timestamp":1745602882000},"page":"75220-75234","source":"Crossref","is-referenced-by-count":0,"title":["On the Challenges of Quantum Circuit Encoding Using Deep and Reinforcement Learning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0912-9801","authenticated-orcid":false,"given":"Patrick","family":"Selig","sequence":"first","affiliation":[{"name":"School of Computer Science, University College Dublin, Dublin 4, Ireland"}]},{"given":"Niall","family":"Murphy","sequence":"additional","affiliation":[{"name":"Equal1 Laboratories, Dublin 4, Ireland"}]},{"given":"David","family":"Redmond","sequence":"additional","affiliation":[{"name":"Equal1 Laboratories, Dublin 4, Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9379-3879","authenticated-orcid":false,"given":"Simon","family":"Caton","sequence":"additional","affiliation":[{"name":"School of Computer Science, University College Dublin, Dublin 4, Ireland"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1103\/physrevlett.129.230504"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41534-024-00805-0"},{"key":"ref3","article-title":"Quantum circuits synthesis using householder transformations","volume":"248","author":"de Brugi\u00e8re","year":"2020","journal-title":"Comput. Phys. Commun."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1120725.1120847"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/qce52317.2021.00041"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/qce57702.2023.00093"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3296802"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00831-9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-07090-4"},{"issue":"15","key":"ref13","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.ifacol.2022.07.602","article-title":"Comparing model-free and model-based algorithms for offline reinforcement learning","volume":"55","author":"Swazinna","year":"2022","journal-title":"IFAC-PapersOnLine"},{"key":"ref14","article-title":"Benchmarking model-based reinforcement learning","author":"Wang","year":"2019","journal-title":"arXiv:1907.02057"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref16","article-title":"Temporal difference models: Model-free deep RL for model-based control","author":"Pong","year":"2018","journal-title":"CoRR"},{"key":"ref17","first-page":"703","article-title":"Combining model-based and model-free updates for trajectory-centric reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chebotar"},{"volume-title":"Combining model-based and model-free RL via multi-step control variates","year":"2018","author":"Che","key":"ref18"},{"key":"ref19","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref20","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref21","article-title":"Quantum circuit optimization with deep reinforcement learning","author":"F\u00f6sel","year":"2021","journal-title":"arXiv:2103.07585"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s42005-021-00684-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41534-019-0141-3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.22331\/q-2022-06-28-747"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2022.3162324"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2813885.2737977"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884786"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3571234"},{"key":"ref29","first-page":"2171","article-title":"Explainable program synthesis by localizing specifications","volume-title":"Proc. OOPSLA","volume":"7","author":"Nazari"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2022.0050"},{"issue":"5","key":"ref31","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/1385-7258(72)90034-0","article-title":"Lambda calculus notation with nameless dummies, a tool for automatic formula manipulation, with application to the church-Rosser theorem","volume":"75","author":"de Bruijn","year":"1972","journal-title":"Indagationes Mathematicae (Proceedings)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1926385.1926423"},{"key":"ref33","first-page":"85","article-title":"Neural-guided program synthesis of information extraction rules using self-supervision","volume-title":"Proc. 1st Workshop Pattern-Based Approaches NLP Age Deep Learn.","author":"Noriega-Atala"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14775"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530173"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275006"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00578"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICEC.1994.350025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1389095.1389343"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1068009.1068292"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-39958-0_13"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205603"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24605-3_37"},{"article-title":"Program synthesis by sketching","year":"2008","author":"Solar-Lezama","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10009-012-0249-7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-54577-5_14"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2737924.2737977"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2737924.2738007"},{"article-title":"DeepCoder: Learning to write programs","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Balog","key":"ref49"},{"key":"ref50","first-page":"990","article-title":"RobustFill: Neural program learning under noisy I\/O","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Devlin"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3192366.3192410"},{"key":"ref52","first-page":"973","article-title":"Unsupervised learning by program synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ellis"},{"key":"ref53","first-page":"6059","article-title":"Learning to infer graphics programs from hand-drawn images","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Ellis"},{"volume-title":"Neural Program Search: Solving Data Processing Tasks From Description and Examples","year":"2018","author":"Polosukhin","key":"ref54"},{"key":"ref55","article-title":"Program synthesis through reinforcement learning guided tree search","author":"Simmons-Edler","year":"2018","journal-title":"arXiv:1806.02932"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/isal_a_00685"},{"key":"ref57","article-title":"Planning with large language models for code generation","author":"Zhang","year":"2023","journal-title":"arXiv:2303.05510"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511976667"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1103\/physrevlett.113.130503"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/nphys3029"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1038\/nature23474"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s41534-024-00858-1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1103\/physreva.109.042401"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.22331\/q-2024-02-15-1257"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-91035-3"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICRC53822.2021.00015"},{"article-title":"Synthesis of quantum circuits with an island genetic algorithm","year":"2021","author":"Miranda","key":"ref67"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-37767-w"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/QCE57702.2023.00093"},{"key":"ref70","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511976667"},{"article-title":"Quantum unitary dataset","year":"2025","author":"Selig","key":"ref72"},{"key":"ref73","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref74","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"issue":"268","key":"ref75","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10976700.pdf?arnumber=10976700","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T04:28:08Z","timestamp":1746592088000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10976700\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3564392","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}