{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T12:25:35Z","timestamp":1764937535187,"version":"3.40.5"},"reference-count":49,"publisher":"Wiley","license":[{"start":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T00:00:00Z","timestamp":1678752000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Bule Hora University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Quantum Engineering"],"published-print":{"date-parts":[[2023,3,14]]},"abstract":"<jats:p>Quantum machine learning uses quantum mechanical concepts of superposition of states to make the decision. In this work, we used these quantum advantages to enhance deep reinforcement learning (DRL). Our primary and foremost goal is to investigate and elucidate a way of representing and solving the frozen lake problems by using PennyLane which contains Xanadu\u2019s back-end quantum processing unit. This paper specifically discusses how to enhance classical deep reinforcement learning algorithms with quantum computing technology, making quantum agents get a maximum reward after a fixed number of epochs and realizing the effect of a number of variational quantum layers on the trainability of enhanced framework. We have analyzed that, as the number of layers increases, the ability of the quantum agent to converge to the optimal state also increases. For this work, we have trained the framework agent with 2, 3, and 5 variational quantum layers. An agent with 2 layers converges to a total reward of 0.95 after the training episode of 526. The other agent with layers converges to a total reward of 0.95 after the training episode of 397 and the agent which uses 5 quantum variational layers converges to a total reward of 0.95 after the training episode of 72. From this, we can understand that the agent with a more variational layer exploits more and converges to the optimal state before the other agent. We also analyzed our work in terms of different learning rate hyperparameters. We recorded every single learning epoch to demonstrate the outcomes of enhanced DRL algorithms with selected 0.1, 0.2, 0.3, and 0.4 learning rates or alpha values. From this result, we can conclude that the greater the learning rate values in quantum deep reinforcement learning, the fewer timesteps it takes to move from the start point to the goal state.<\/jats:p>","DOI":"10.1155\/2023\/2451990","type":"journal-article","created":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T19:35:05Z","timestamp":1678822505000},"page":"1-16","source":"Crossref","is-referenced-by-count":6,"title":["Investigating the Effects of Hyperparameters in Quantum-Enhanced Deep Reinforcement Learning"],"prefix":"10.1155","volume":"2023","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0921-8375","authenticated-orcid":true,"given":"Getahun","family":"Fikadu Tilaye","sequence":"first","affiliation":[{"name":"College of Informatics, Software Engineering Department, Bule Hora University, Bule Hora, Ethiopia"}]},{"given":"Amit","family":"Pandey","sequence":"additional","affiliation":[{"name":"College of Informatics, Computer Science Department, Bule Hora University, Bule Hora, Ethiopia"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1038\/nature23474"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1007\/s42484-021-00046-w"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.2978071"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn48605.2020.9207714"},{"article-title":"Quantum machine learning: fad or future?","year":"2021","author":"A. Ishtiaq","key":"6"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.22331\/q-2018-08-06-79"},{"article-title":"The bitter truth about gate-based quantum algorithms in the NISQ era the bitter truth about gate-based quantum algorithms in the NISQ era","year":"2020","author":"F. Leymann","key":"8"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.117.130501"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2021.0121092"},{"key":"11","first-page":"1","article-title":"Quantum algorithms for supervised and unsupervised machine learning","author":"S. Lloyd","year":"2013"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v16i1.7437"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010470"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.4236\/jqis.2019.91001"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.4.031002"},{"key":"16","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-25928-2_14","article-title":"Toward quantum computational agents","volume-title":"Agents and Computational Autonomy","author":"M. Klusch","year":"2004"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.3389\/fphy.2017.00071"},{"key":"18","first-page":"1","article-title":"Multiqubit and multilevel quantum reinforcement learning with quantum technologies","author":"L. Lamata","year":"2018"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03242-7"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2021.126582"},{"article-title":"Adaptive discrete communication bottlenecks with dynamic vector quantization","year":"2022","author":"D. Liu","key":"21"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-01711-6"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1002\/qute.201800074"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.925743"},{"article-title":"Machine learning for quantum and complex systems","year":"2020","author":"D. Amelia","key":"25"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4095-0_4"},{"key":"27","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"V. Mnih","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"article-title":"Asynchronous methods for model-based reinforcement learning","year":"2019","author":"Y. Zhang","key":"29"},{"key":"30","first-page":"1","article-title":"Untangling the HPC innovation dilemma through quantum computing executive summary","author":"U. The","year":"2021"},{"article-title":"Reinforcement learning with quantum variational circuits","year":"2008","author":"O. Lockwood","key":"31"},{"article-title":"Variational quantum soft actor-critic","year":"2021","author":"Q. Lan","key":"32"},{"article-title":"Ntroduction to quantum reinforcement learning theory and PennyLane-based implementation","year":"2021","author":"W. J. Yun","key":"33"},{"article-title":"An assessment of the U . S . and Chinese industrial bases in quantum technology","year":"2022","author":"E. Parker","key":"34"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.1145\/3386162"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-021-01588-6"},{"article-title":"Commercialize early quantum technologies","year":"2017","author":"M. Mohseni","key":"37"},{"key":"38","first-page":"1","article-title":"Quantum architecture search via deep reinforcement learning","author":"E. J. Kuo","year":"2021"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413453"},{"key":"40","first-page":"2019","article-title":"A tutorial on quantum convolutional neural networks ( QCNN )","author":"J. Choi","year":"2020"},{"article-title":"Qgan quantized generative adversarial networks","year":"2018","author":"P. Wang","key":"41"},{"key":"42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3037931"},{"key":"43","first-page":"1","article-title":"OpenAI gym","author":"G. Brockman","year":"2016"},{"key":"44","first-page":"1","article-title":"PennyLane: automatic differentiation of hybrid quantum-classical computations","author":"V. Bergholm","year":"2018"},{"key":"45","doi-asserted-by":"crossref","DOI":"10.18297\/etd\/3433","article-title":"Exploring information for quantum machine learning models","author":"M. Telahun","year":"2020"},{"key":"46","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-96424-9","volume-title":"Supervised Learning With Quantum Computers","author":"M. Schuld","year":"2018"},{"key":"47","first-page":"1","article-title":"Efficient realization of quantum primitives for Shor\u2019s algorithm using PennyLane library","author":"A. V. Antipov","year":"2022"},{"article-title":"Quantum machine learning for classical data","year":"2021","author":"L. Wossnig","key":"48"},{"key":"49","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3155196"}],"container-title":["Quantum Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/que\/2023\/2451990.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/que\/2023\/2451990.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/que\/2023\/2451990.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T19:35:16Z","timestamp":1678822516000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/que\/2023\/2451990\/"}},"subtitle":[],"editor":[{"given":"Shi Hai","family":"Dong","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,3,14]]},"references-count":49,"alternative-id":["2451990","2451990"],"URL":"https:\/\/doi.org\/10.1155\/2023\/2451990","relation":{},"ISSN":["2577-0470"],"issn-type":[{"type":"electronic","value":"2577-0470"}],"subject":[],"published":{"date-parts":[[2023,3,14]]}}}