{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T05:16:26Z","timestamp":1779340586533,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T00:00:00Z","timestamp":1739232000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T00:00:00Z","timestamp":1739232000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["Momentum"],"award-info":[{"award-number":["Momentum"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Quantum Mach. Intell."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s42484-024-00226-4","type":"journal-article","created":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T11:31:01Z","timestamp":1739273461000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Nav-Q: quantum deep reinforcement learning for collision-free navigation of self-driving cars"],"prefix":"10.1007","volume":"7","author":[{"given":"Akash","family":"Sinha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Macaluso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Klusch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,11]]},"reference":[{"issue":"9","key":"226_CR1","doi-asserted-by":"publisher","first-page":"14043","DOI":"10.1109\/TITS.2021.3134702","volume":"23","author":"Z Zhu","year":"2021","unstructured":"Zhu Z, Zhao H (2021) A survey of deep RL and IL for autonomous driving policy learning. IEEE Trans Intell Transp Syst 23(9):14043\u201314065","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"226_CR2","doi-asserted-by":"publisher","unstructured":"Chib PS, Singh P (2023) Recent advancements in end-to-end autonomous driving using deep learning: a survey. IEEE Trans Intell Veh 1\u201318. https:\/\/doi.org\/10.1109\/TIV.2023.3318070","DOI":"10.1109\/TIV.2023.3318070"},{"issue":"6","key":"226_CR3","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","volume":"23","author":"BR Kiran","year":"2021","unstructured":"Kiran BR, Sobh I, Talpaert V, Mannion P, Al Sallab AA, Yogamani S, P\u00e9rez P (2021) Deep reinforcement learning for autonomous driving: a survey. IEEE Trans Intell Transp Syst 23(6):4909\u20134926","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"226_CR4","doi-asserted-by":"publisher","unstructured":"Pusse F, Klusch M (2019) Hybrid online POMDP planning and deep reinforcement learning for safer self-driving cars. In: 2019 IEEE intelligent vehicles symposium (IV), pp 1013\u20131020. https:\/\/doi.org\/10.1109\/IVS.2019.8814125","DOI":"10.1109\/IVS.2019.8814125"},{"key":"226_CR5","doi-asserted-by":"publisher","unstructured":"Gupta D, Klusch M (2023) HyLEAR: hybrid deep reinforcement learning and planning for safe and comfortable automated driving. In: 2023 IEEE intelligent vehicles symposium (IV), pp 1\u20138. https:\/\/doi.org\/10.1109\/IV55152.2023.10186781","DOI":"10.1109\/IV55152.2023.10186781"},{"key":"226_CR6","first-page":"28362","volume":"34","author":"S Jerbi","year":"2021","unstructured":"Jerbi S, Gyurik C, Marshall S, Briegel H, Dunjko V (2021) Parametrized quantum policies for reinforcement learning. Adv Neural Inf Process Syst 34:28362\u201328375","journal-title":"Adv Neural Inf Process Syst"},{"key":"226_CR7","unstructured":"Lan Q (2021) Variational quantum soft actor-critic. arXiv:2112.11921"},{"key":"226_CR8","doi-asserted-by":"publisher","first-page":"141007","DOI":"10.1109\/ACCESS.2020.3010470","volume":"8","author":"SY-C Chen","year":"2020","unstructured":"Chen SY-C, Yang C-HH, Qi J, Chen P-Y, Ma X, Goan H-S (2020) Variational quantum circuits for deep reinforcement learning. IEEE Access 8:141007\u2013141024","journal-title":"IEEE Access"},{"key":"226_CR9","doi-asserted-by":"publisher","first-page":"720","DOI":"10.22331\/q-2022-05-24-720","volume":"6","author":"A Skolik","year":"2022","unstructured":"Skolik A, Jerbi S, Dunjko V (2022) Quantum agents in the gym: a variational quantum algorithm for deep Q-learning. Quantum 6:720","journal-title":"Quantum"},{"key":"226_CR10","unstructured":"Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J, Zaremba W (2016) OpenAI Gym. arXiv:1606.01540"},{"key":"226_CR11","doi-asserted-by":"publisher","first-page":"226","DOI":"10.22331\/q-2020-02-06-226","volume":"4","author":"A P\u00e9rez-Salinas","year":"2020","unstructured":"P\u00e9rez-Salinas A, Cervera-Lierta A, Gil-Fuster E, Latorre JI (2020) Data re-uploading for a universal quantum classifier. Quantum 4:226","journal-title":"Quantum"},{"key":"226_CR12","unstructured":"Mnih V, Badia AP, Mirza M, Graves A, Lillicrap T, Harley T, Silver D, Kavukcuoglu K (2016) Asynchronous methods for deep reinforcement learning. In: International conference on machine learning, pp 1928\u20131937. PMLR"},{"key":"226_CR13","unstructured":"Mirowski P, Pascanu R, Viola F, Soyer H, Ballard AJ, Banino A, Denil M, Goroshin R, Sifre L, Kavukcuoglu K et al (2016) Learning to navigate in complex environments. arXiv:1611.03673"},{"key":"226_CR14","doi-asserted-by":"publisher","first-page":"10357","DOI":"10.1109\/ACCESS.2021.3050338","volume":"9","author":"M Everett","year":"2021","unstructured":"Everett M, Chen YF, How JP (2021) Collision avoidance in pedestrian-rich environments with deep reinforcement learning. IEEE Access 9:10357\u201310377","journal-title":"IEEE Access"},{"issue":"8","key":"226_CR15","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput"},{"key":"226_CR16","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv:1707.06347"},{"key":"226_CR17","doi-asserted-by":"crossref","unstructured":"Tang Y (2019) Towards learning multi-agent negotiations via self-play. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops","DOI":"10.1109\/ICCVW.2019.00297"},{"key":"226_CR18","unstructured":"Bergholm V, Izaac J, Schuld M, Gogolin C, Ahmed S, Ajith V, Alam MS, Alonso-Linaje G, AkashNarayanan B, Asadi A, et al (2018) PennyLane: automatic differentiation of hybrid quantum-classical computations. arXiv:1811.04968"},{"key":"226_CR19","doi-asserted-by":"crossref","unstructured":"Lockwood O, Si M (2020) Reinforcement learning with quantum variational circuit. In: Proceedings of the AAAI conference on artificial intelligence and interactive digital entertainment, vol 16, pp 245\u2013251","DOI":"10.1609\/aiide.v16i1.7437"},{"key":"226_CR20","unstructured":"Acuto A, Barill\u00e0 P, Bozzolo L, Conterno M, Pavese M, Policicchio A (2022) Variational quantum soft actor-critic for robotic arm control. arXiv:2212.11681"},{"key":"226_CR21","unstructured":"Sutton RS, McAllester D, Singh S, Mansour Y (1999) Policy gradient methods for reinforcement learning with function approximation. Adv Neural Inf Process Syst 12"},{"key":"226_CR22","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1109\/37.236324","volume":"13","author":"S Geva","year":"1993","unstructured":"Geva S, Sitte J (1993) A cartpole experiment benchmark for trainable controllers. Control Syst IEEE 13:40\u201351. https:\/\/doi.org\/10.1109\/37.236324","journal-title":"Control Syst IEEE"},{"key":"226_CR23","doi-asserted-by":"crossref","unstructured":"Kwak Y, Yun WJ, Jung S, Kim J-K, Kim J (2021) Introduction to quantum reinforcement learning: theory and PennyLane-based implementation. In: 2021 International conference on Information and Communication Technology Convergence (ICTC), pp 416\u2013420. IEEE","DOI":"10.1109\/ICTC52510.2021.9620885"},{"issue":"1","key":"226_CR24","first-page":"3511029","volume":"2021","author":"T Kimura","year":"2021","unstructured":"Kimura T, Shiba K, Chen C-C, Sogabe M, Sakamoto K, Sogabe T (2021) Variational quantum circuit-based reinforcement learning for POMDP and experimental implementation. Math Probl Eng 2021(1):3511029","journal-title":"Math Probl Eng"},{"issue":"8","key":"226_CR25","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/s11128-023-04051-9","volume":"22","author":"NF Bar","year":"2023","unstructured":"Bar NF, Yetis H, Karakose M (2023) An efficient and scalable variational quantum circuits approach for deep reinforcement learning. Quantum Inf Process 22(8):300","journal-title":"Quantum Inf Process"},{"key":"226_CR26","unstructured":"Tschiatschek S, Arulkumaran K, St\u00fchmer J, Hofmann K (2018) Variational inference for data-efficient model learning in POMDPs. arXiv:1805.09281"},{"key":"226_CR27","doi-asserted-by":"crossref","unstructured":"Kandala A, Mezzacapo A, Temme K, Takita M, Brink M, Chow JM, Gambetta JM (2017) Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets. Nature 549(7671):242\u2013246","DOI":"10.1038\/nature23879"},{"key":"226_CR28","unstructured":"Dosovitskiy A, Ros G, Codevilla F, Lopez A, Koltun V (2017) CARLA: an open urban driving simulator. In: Conference on robot learning, pp 1\u201316. PMLR"},{"key":"226_CR29","unstructured":"Bartels B, Erbsmehl C (2014) Bewegungsverhalten von fu\u00dfg\u00e4ngern im stra\u00dfenverkehr, teil 1. FAT-Schriftenreihe (267)"},{"key":"226_CR30","unstructured":"Ba JL, Kiros JR, Hinton GE (2016) Layer normalization. arXiv:1607.06450"},{"issue":"3","key":"226_CR31","doi-asserted-by":"publisher","first-page":"032309","DOI":"10.1103\/PhysRevA.98.032309","volume":"98","author":"K Mitarai","year":"2018","unstructured":"Mitarai K, Negoro M, Kitagawa M, Fujii K (2018) Quantum circuit learning. Phys Rev A 98(3):032309","journal-title":"Phys Rev A"},{"key":"226_CR32","doi-asserted-by":"crossref","unstructured":"Schuld M, Bergholm V, Gogolin C, Izaac J, Killoran N (2019) Evaluating analytic gradients on quantum hardware. Phys Rev A 99(3):032331","DOI":"10.1103\/PhysRevA.99.032331"},{"key":"226_CR33","unstructured":"Rigetti Computing (2023) Quantum gate errors - PyQuil documentation. Website. https:\/\/pyquil-docs.rigetti.com\/en\/stable\/noise.html#quantum-gate-errors"},{"issue":"1","key":"226_CR34","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TIT.2002.806153","volume":"49","author":"C King","year":"2003","unstructured":"King C (2003) The capacity of the quantum depolarizing channel. IEEE Trans Inf Theory 49(1):221\u2013229","journal-title":"IEEE Trans Inf Theory"},{"key":"226_CR35","unstructured":"Berezniuk O, Figalli A, Ghigliazza R, Musaelian K (2020) A scale-dependent notion of effective dimension. arXiv:2001.10872"},{"issue":"6","key":"226_CR36","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1038\/s43588-021-00084-1","volume":"1","author":"A Abbas","year":"2021","unstructured":"Abbas A, Sutter D, Zoufal C, Lucchi A, Figalli A, Woerner S (2021) The power of quantum neural networks. Nat Comput Sci 1(6):403\u2013409","journal-title":"Nat Comput Sci"},{"key":"226_CR37","doi-asserted-by":"publisher","first-page":"214","DOI":"10.22331\/q-2019-12-09-214","volume":"3","author":"E Grant","year":"2019","unstructured":"Grant E, Wossnig L, Ostaszewski M, Benedetti M (2019) An initialization strategy for addressing barren plateaus in parametrized quantum circuits. Quantum 3:214","journal-title":"Quantum"},{"key":"226_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42484-020-00036-4","volume":"3","author":"A Skolik","year":"2021","unstructured":"Skolik A, McClean JR, Mohseni M, Smagt P, Leib M (2021) Layerwise learning for quantum neural networks. Quantum Mach Intell 3:1\u201311","journal-title":"Quantum Mach Intell"},{"issue":"1","key":"226_CR39","doi-asserted-by":"publisher","first-page":"010313","DOI":"10.1103\/PRXQuantum.3.010313","volume":"3","author":"Z Holmes","year":"2022","unstructured":"Holmes Z, Sharma K, Cerezo M, Coles PJ (2022) Connecting ansatz expressibility to gradient magnitudes and barren plateaus. PRX Quantum 3(1):010313","journal-title":"PRX Quantum"},{"key":"226_CR40","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press"},{"issue":"4","key":"226_CR41","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1137\/0330046","volume":"30","author":"BT Polyak","year":"1992","unstructured":"Polyak BT, Juditsky AB (1992) Acceleration of stochastic approximation by averaging. SIAM J Control Optim 30(4):838\u2013855","journal-title":"SIAM J Control Optim"}],"container-title":["Quantum Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-024-00226-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42484-024-00226-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42484-024-00226-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T10:40:27Z","timestamp":1750934427000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42484-024-00226-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,11]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["226"],"URL":"https:\/\/doi.org\/10.1007\/s42484-024-00226-4","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3796117\/v1","asserted-by":"object"}]},"ISSN":["2524-4906","2524-4914"],"issn-type":[{"value":"2524-4906","type":"print"},{"value":"2524-4914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,11]]},"assertion":[{"value":"23 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"19"}}