{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T21:08:17Z","timestamp":1779311297466,"version":"3.51.4"},"reference-count":77,"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\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3506656","type":"journal-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:41:56Z","timestamp":1732736516000},"page":"179396-179417","source":"Crossref","is-referenced-by-count":9,"title":["Optimization of Reinforcement Learning Using Quantum Computation"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6348-3228","authenticated-orcid":false,"given":"Roopa","family":"Ravish","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, PES University, Ring Road Campus, Bengaluru, Karnataka, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7222-7335","authenticated-orcid":false,"given":"Nischal R.","family":"Bhat","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, PES University, Ring Road Campus, Bengaluru, Karnataka, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5632-2227","authenticated-orcid":false,"given":"N.","family":"Nandakumar","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, PES University, Ring Road Campus, Bengaluru, Karnataka, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1272-8364","authenticated-orcid":false,"given":"S.","family":"Sagar","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, PES University, Ring Road Campus, Bengaluru, Karnataka, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1958-6592","authenticated-orcid":false,"family":"Sunil","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, PES University, Ring Road Campus, Bengaluru, Karnataka, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7493-6221","authenticated-orcid":false,"given":"Prasad B.","family":"Honnavalli","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, PES University, Ring Road Campus, Bengaluru, Karnataka, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-41217-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-024-00770-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.22331\/q-2018-08-06-79"},{"key":"ref4","article-title":"Variational quantum soft actor-critic for robotic arm control","author":"Acuto","year":"2022","journal-title":"arXiv:2212.11681"},{"key":"ref5","article-title":"Unentangled quantum reinforcement learning agents in the OpenAI gym","author":"Hsiao","year":"2022","journal-title":"arXiv:2203.14348"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature08812"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac4559"},{"key":"ref10","article-title":"Modeling and interpreting real-world human risk decision making with inverse reinforcement learning","author":"Liu","year":"2019","journal-title":"arXiv:1906.05803"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC52510.2021.9620885"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/18\/2\/023023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.92.042303"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/aab822"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s42454-021-00025-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/11539117_97"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app11188589"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683463"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.12.011059"},{"key":"ref20","volume-title":"The Hugging Face Deep Reinforcement Learning Class","author":"Simonini","year":"2023"},{"key":"ref21","article-title":"A survey on quantum reinforcement learning","author":"Meyer","year":"2022","journal-title":"arXiv:2211.03464"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.81.865"},{"key":"ref24","article-title":"Quantum inspire","author":"Voorhoede","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.22331\/q-2019-10-07-191"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature23474"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ab9803"},{"key":"ref28","article-title":"Quantum deep recurrent reinforcement learning","author":"Chen","year":"2022","journal-title":"arXiv:2210.14876"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2022.08.004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122616"},{"key":"ref31","volume-title":"Optimization of Reinforcement Learning Using Quantum Computation","author":"Bhat","year":"2024"},{"key":"ref32","article-title":"Reinforcement learning with blackjack","author":"Mao","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3345768.3355908"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref35","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref36","article-title":"Quantum reinforcement learning for solving a stochastic frozen lake environment and the impact of quantum architecture choices","author":"Dr\u0103gan","year":"2022","journal-title":"arXiv:2212.07932"},{"key":"ref37","article-title":"Minigrid & miniworld: Modular & customizable reinforcement learning environments for goal-oriented tasks","author":"Chevalier-Boisvert","year":"2023","journal-title":"arXiv:2306.13831"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25872"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-021-00348-9"},{"key":"ref40","first-page":"18182","article-title":"Reinforcement learning for optimization of variational quantum circuit architectures","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ostaszewski"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010470"},{"key":"ref42","article-title":"Quantum control based on deep reinforcement learning","author":"Wang","year":"2022","journal-title":"arXiv:2212.07385"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v16i1.7437"},{"key":"ref44","article-title":"Reinforcement-learning-based variational quantum circuits optimization for combinatorial problems","author":"Khairy","year":"2019","journal-title":"arXiv:1911.04574"},{"key":"ref45","article-title":"Reinforcement learning assisted recursive QAOA","author":"Patel","year":"2022","journal-title":"arXiv:2207.06294"},{"key":"ref46","article-title":"Quantum circuit optimization with deep reinforcement learning","author":"F\u00f6sel","year":"2021","journal-title":"arXiv:2103.07585"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.10.021067"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/en15166034"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCIS51004.2021.9397241"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps52748.2021.9682182"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2024.109031"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3090305"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/9761157"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3318173"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1140\/epjqt\/s40507-023-00166-1"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.22331\/q-2023-09-26-1122"},{"key":"ref57","first-page":"1","article-title":"Parametrized quantum policies for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jerbi"},{"key":"ref58","article-title":"PennyLane: Automatic differentiation of hybrid quantum-classical computations","author":"Bergholm","year":"2018","journal-title":"arXiv:1811.04968"},{"key":"ref59","article-title":"Quantum deep reinforcement learning for robot navigation tasks","author":"Hohenfeld","year":"2022","journal-title":"arXiv:2202.12180"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/GUCON.2018.8675050"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747369"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.105.062443"},{"key":"ref63","article-title":"Quantum reinforcement learning in continuous action space","author":"Wu","year":"2020","journal-title":"arXiv:2012.10711"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368199"},{"key":"ref65","article-title":"Deep reinforcement learning in large discrete action spaces","author":"Dulac-Arnold","year":"2015","journal-title":"arXiv:1512.07679"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.125.100401"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0200455"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.031084"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1088\/0034-4885\/76\/7\/076001"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03242-7"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s42484-023-00116-1"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.18.024033"},{"key":"ref73","article-title":"Error-mitigated multi-layer quantum routing","author":"Shi","year":"2024","journal-title":"arXiv:2409.14632"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.3390\/math12142235"},{"key":"ref75","volume-title":"Differences in Error Suppression, Mitigation, and Correction | IBM Quantum Computing Blog \u2014 Ibm.com","year":"2024"},{"key":"ref76","volume-title":"Exploring Error Mitigation With the Mthree Qiskit Extension | IBM Quantum Computing Blog\u2014Ibm.com","year":"2024"},{"key":"ref77","volume-title":"Landmark IBM Error Correction Paper on Nature Cover | IBM Quantum Computing Blog\u2014Ibm.com","year":"2024"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10767681.pdf?arnumber=10767681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:19:16Z","timestamp":1733883556000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10767681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3506656","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}