{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:10:28Z","timestamp":1784736628419,"version":"3.55.0"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Wireless Pers Commun"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s11277-024-11714-y","type":"journal-article","created":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T09:21:43Z","timestamp":1735896103000},"page":"2253-2283","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Maximizing Energy Harvesting with the Aid of Reconfigurable Intelligent Surface for UAV Using Proximal Policy Optimization Algorithm"],"prefix":"10.1007","volume":"139","author":[{"given":"Praveen","family":"Kumar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rallabhandi S. K.","family":"Mahesh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Priyadarshni","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajiv","family":"Misra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"issue":"9","key":"11714_CR1","doi-asserted-by":"publisher","first-page":"5957","DOI":"10.1109\/TWC.2023.3238808","volume":"22","author":"SK Singh","year":"2023","unstructured":"Singh, S. K., Agrawal, K., Singh, K., Clerckx, B., & Li, C.-P. (2023). RSMA for hybrid RIS-UAV-aided full-duplex communications with finite blocklength codes under imperfect SIC. IEEE Transactions on Wireless Communications, 22(9), 5957\u20135975. https:\/\/doi.org\/10.1109\/TWC.2023.3238808","journal-title":"IEEE Transactions on Wireless Communications"},{"issue":"3","key":"11714_CR2","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1109\/TCCN.2020.2992604","volume":"6","author":"MA ElMossallamy","year":"2020","unstructured":"ElMossallamy, M. A., Zhang, H., Song, L., Seddik, K. G., Han, Z., & Li, G. Y. (2020). Reconfigurable intelligent surfaces for wireless communications: Principles, challenges, and opportunities. IEEE Transactions on Cognitive Communications and Networking, 6(3), 990\u20131002.","journal-title":"IEEE Transactions on Cognitive Communications and Networking"},{"key":"11714_CR3","doi-asserted-by":"publisher","first-page":"116753","DOI":"10.1109\/ACCESS.2019.2935192","volume":"7","author":"E Basar","year":"2019","unstructured":"Basar, E., Di Renzo, M., De Rosny, J., Debbah, M., Alouini, M.-S., & Zhang, R. (2019). Wireless communications through reconfigurable intelligent surfaces. IEEE access, 7, 116753\u2013116773.","journal-title":"IEEE access"},{"issue":"5","key":"11714_CR4","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/LWC.2020.2969167","volume":"9","author":"K Feng","year":"2020","unstructured":"Feng, K., Wang, Q., Li, X., & Wen, C.-K. (2020). Deep reinforcement learning based intelligent reflecting surface optimization for miso communication systems. IEEE Wireless Communications Letters, 9(5), 745\u2013749.","journal-title":"IEEE Wireless Communications Letters"},{"key":"11714_CR5","doi-asserted-by":"crossref","unstructured":"Balakrishnan, A., De, S., & Wang, L.-C. (2020). Traffic skewness-aware performance analysis of dual-powered green cellular networks. In: GLOBECOM 2020-2020 IEEE Global Communications Conference, pp. 1\u20136 . IEEE","DOI":"10.1109\/GLOBECOM42002.2020.9322397"},{"key":"11714_CR6","doi-asserted-by":"crossref","unstructured":"Peng, H., Wang, L.-C., Li, G.Y., & Tsai, A.-H. (2022). Long-lasting uav-aided ris communications based on swipt. In: 2022 IEEE Wireless Communications and Networking Conference (WCNC), pp. 1844\u20131849. IEEE","DOI":"10.1109\/WCNC51071.2022.9771999"},{"issue":"1","key":"11714_CR7","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1109\/TCCN.2021.3115765","volume":"8","author":"H Peng","year":"2021","unstructured":"Peng, H., Tsai, A.-H., Wang, L.-C., & Han, Z. (2021). Leopard: Parallel optimal deep echo state network prediction improves service coverage for uav-assisted outdoor hotspots. IEEE Transactions on Cognitive Communications and Networking, 8(1), 282\u2013295.","journal-title":"IEEE Transactions on Cognitive Communications and Networking"},{"key":"11714_CR8","doi-asserted-by":"crossref","unstructured":"Lee, G., Jung, M., Kasgari, A.T.Z., Saad, W., & Bennis, M. (2020). Deep reinforcement learning for energy-efficient networking with reconfigurable intelligent surfaces. In: ICC 2020-2020 IEEE International Conference on Communications (ICC), pp. 1\u20136. IEEE","DOI":"10.1109\/ICC40277.2020.9149380"},{"key":"11714_CR9","doi-asserted-by":"publisher","first-page":"2147","DOI":"10.1007\/s11276-021-02562-w","volume":"27","author":"M Lei","year":"2021","unstructured":"Lei, M., Zhang, X., Yu, B., Fowler, S., & Yu, B. (2021). Throughput maximization for UAV-assisted wireless powered d2d communication networks with a hybrid time division duplex\/frequency division duplex scheme. Wireless Networks, 27, 2147\u20132157.","journal-title":"Wireless Networks"},{"key":"11714_CR10","doi-asserted-by":"crossref","unstructured":"Boulogeorgos, A.-A.A., & Alexiou, A. (2023). On the ergodic secrecy capacity of reconfigurable intelligent surface aided wireless systems under mixture gamma fading. In: 2023 IEEE Wireless Communications and Networking Conference (WCNC), pp. 1\u20136. IEEE","DOI":"10.1109\/WCNC55385.2023.10118925"},{"issue":"7","key":"11714_CR11","doi-asserted-by":"publisher","first-page":"1586","DOI":"10.1109\/LWC.2021.3074990","volume":"10","author":"H Mei","year":"2021","unstructured":"Mei, H., Yang, K., Shen, J., & Liu, Q. (2021). Joint trajectory-task-cache optimization with phase-shift design of RIS-assisted UAV for MEC. IEEE Wireless Communications Letters, 10(7), 1586\u20131590.","journal-title":"IEEE Wireless Communications Letters"},{"issue":"5","key":"11714_CR12","doi-asserted-by":"publisher","first-page":"2792","DOI":"10.1109\/TWC.2020.3044302","volume":"20","author":"Y Chen","year":"2020","unstructured":"Chen, Y., Ai, B., Zhang, H., Niu, Y., Song, L., Han, Z., & Poor, H. V. (2020). Reconfigurable intelligent surface assisted device-to-device communications. IEEE Transactions on Wireless Communications, 20(5), 2792\u20132804.","journal-title":"IEEE Transactions on Wireless Communications"},{"key":"11714_CR13","doi-asserted-by":"crossref","unstructured":"Li, J., & Liu, J. (2020). Sum rate maximization via reconfigurable intelligent surface in uav communication: Phase shift and trajectory optimization. In: 2020 IEEE\/CIC International Conference on Communications in China (ICCC), pp. 124\u2013129. IEEE","DOI":"10.1109\/ICCC49849.2020.9238910"},{"issue":"2","key":"11714_CR14","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/MVT.2019.2903655","volume":"14","author":"Z Xiong","year":"2019","unstructured":"Xiong, Z., Zhang, Y., Niyato, D., Deng, R., Wang, P., & Wang, L.-C. (2019). Deep reinforcement learning for mobile 5g and beyond: Fundamentals, applications, and challenges. IEEE Vehicular Technology Magazine, 14(2), 44\u201352.","journal-title":"IEEE Vehicular Technology Magazine"},{"issue":"3","key":"11714_CR15","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1109\/JSTSP.2021.3134162","volume":"16","author":"KK Nguyen","year":"2021","unstructured":"Nguyen, K. K., Khosravirad, S. R., Da Costa, D. B., Nguyen, L. D., & Duong, T. Q. (2021). Reconfigurable intelligent surface-assisted multi-UAV networks: Efficient resource allocation with deep reinforcement learning. IEEE Journal of Selected Topics in Signal Processing, 16(3), 358\u2013368.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"issue":"4","key":"11714_CR16","doi-asserted-by":"publisher","first-page":"3978","DOI":"10.1109\/TVT.2021.3063953","volume":"70","author":"M Samir","year":"2021","unstructured":"Samir, M., Elhattab, M., Assi, C., Sharafeddine, S., & Ghrayeb, A. (2021). Optimizing age of information through aerial reconfigurable intelligent surfaces: A deep reinforcement learning approach. IEEE Transactions on Vehicular Technology, 70(4), 3978\u20133983.","journal-title":"IEEE Transactions on Vehicular Technology"},{"issue":"4","key":"11714_CR17","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/MWC.004.2100694","volume":"29","author":"I Ahmad","year":"2022","unstructured":"Ahmad, I., Narmeen, R., Becvar, Z., & Guvenc, I. (2022). Machine learning-based beamforming for unmanned aerial vehicles equipped with reconfigurable intelligent surfaces. IEEE Wireless Communications, 29(4), 32\u201338.","journal-title":"IEEE Wireless Communications"},{"key":"11714_CR18","unstructured":"Brighente, A., Conti, M., Idriss, H., & Tomasin, S. (2022). Unmanned aerial vehicles meet reflective intelligent surfaces to improve coverage and secrecy. arXiv preprint arXiv:2205.02506"},{"key":"11714_CR19","first-page":"11767","volume":"33","author":"L Pan","year":"2020","unstructured":"Pan, L., Cai, Q., & Huang, L. (2020). Softmax deep double deterministic policy gradients. Advances in Neural Information Processing Systems, 33, 11767\u201311777.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"11714_CR20","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2024.3357356","author":"A Ranjha","year":"2024","unstructured":"Ranjha, A., Naboulsi, D., Emary, M. E., & Gagnon, F. (2024). Facilitating URLLC vis-\u00e1-vis UAV-enabled relaying for MEC systems in 6-G networks. IEEE Transactions on Reliability. https:\/\/doi.org\/10.1109\/TR.2024.3357356","journal-title":"IEEE Transactions on Reliability"},{"issue":"3","key":"11714_CR21","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1109\/JSTSP.2021.3134162","volume":"16","author":"KK Nguyen","year":"2021","unstructured":"Nguyen, K. K., Khosravirad, S. R., Da Costa, D. B., Nguyen, L. D., & Duong, T. Q. (2021). Reconfigurable intelligent surface-assisted multi-UAV networks: Efficient resource allocation with deep reinforcement learning. IEEE Journal of Selected Topics in Signal Processing, 16(3), 358\u2013368.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"11714_CR22","doi-asserted-by":"crossref","unstructured":"Long, H., Chen, M., Yang, Z., Wang, B., Li, Z., Yun, X., & Shikh-Bahaei, M. (2020). Reflections in the sky: Joint trajectory and passive beamforming design for secure uav networks with reconfigurable intelligent surface. arXiv preprint arXiv:2005.10559","DOI":"10.1109\/GCWkshps50303.2020.9367542"},{"key":"11714_CR23","doi-asserted-by":"crossref","unstructured":"Ranjha, A., Javed, M.A., Piran, M.J., Asif, M., Hussien, M., Zeadally, S., & Frnda, J. (2023). Towards facilitating power efficient urllc systems in uav networks under jittering. IEEE Transactions on Consumer Electronics.","DOI":"10.1109\/TCE.2023.3305550"},{"issue":"6","key":"11714_CR24","doi-asserted-by":"publisher","first-page":"4071","DOI":"10.1109\/TNSE.2023.3282870","volume":"10","author":"A Ranjha","year":"2023","unstructured":"Ranjha, A., Javed, M. A., Srivastava, G., & Asif, M. (2023). Quasi-optimization of resource allocation and positioning for solar-powered UAVs. IEEE Transactions on Network Science and Engineering, 10(6), 4071\u20134081.","journal-title":"IEEE Transactions on Network Science and Engineering"},{"issue":"2","key":"11714_CR25","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1109\/TWC.2022.3165853","volume":"22","author":"Y Cang","year":"2022","unstructured":"Cang, Y., Chen, M., Zhao, J., Yang, Z., Hu, Y., Huang, C., & Wong, K.-K. (2022). Joint deployment and resource management for VLC-enabled RISs-assisted UAV networks. IEEE Transactions on Wireless Communications, 22(2), 746\u2013760.","journal-title":"IEEE Transactions on Wireless Communications"},{"issue":"5","key":"11714_CR26","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1109\/MWC.001.1900534","volume":"27","author":"C Huang","year":"2020","unstructured":"Huang, C., Hu, S., Alexandropoulos, G. C., Zappone, A., Yuen, C., Zhang, R., Di Renzo, M., & Debbah, M. (2020). Holographic MIMO surfaces for 6g wireless networks: Opportunities, challenges, and trends. IEEE wireless communications, 27(5), 118\u2013125.","journal-title":"IEEE wireless communications"},{"issue":"5","key":"11714_CR27","doi-asserted-by":"publisher","first-page":"1112","DOI":"10.1109\/JSTSP.2022.3176140","volume":"16","author":"L Wei","year":"2022","unstructured":"Wei, L., Huang, C., Alexandropoulos, G. C., Wei, E., Zhang, Z., Debbah, M., & Yuen, C. (2022). Multi-user holographic MIMO surfaces: Channel modeling and spectral efficiency analysis. IEEE Journal of Selected Topics in Signal Processing, 16(5), 1112\u20131124.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"11714_CR28","doi-asserted-by":"crossref","unstructured":"Nguyen, T.-H., Park, H., & Park, L. (2023). Recent studies on deep reinforcement learning in ris-uav communication networks. In: 2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pp. 378\u2013381. IEEE","DOI":"10.1109\/ICAIIC57133.2023.10067052"},{"key":"11714_CR29","doi-asserted-by":"crossref","unstructured":"Long, H., Chen, M., Yang, Z., Wang, B., Li, Z., Yun, X., & Shikh-Bahaei, M. (2020). Reflections in the sky: Joint trajectory and passive beamforming design for secure uav networks with reconfigurable intelligent surface. arXiv preprint arXiv:2005.10559.","DOI":"10.1109\/GCWkshps50303.2020.9367542"},{"issue":"1","key":"11714_CR30","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1109\/TWC.2021.3098632","volume":"21","author":"Z Yang","year":"2021","unstructured":"Yang, Z., Chen, M., Saad, W., Xu, W., Shikh-Bahaei, M., Poor, H. V., & Cui, S. (2021). Energy-efficient wireless communications with distributed reconfigurable intelligent surfaces. IEEE Transactions on Wireless Communications, 21(1), 665\u2013679.","journal-title":"IEEE Transactions on Wireless Communications"},{"key":"11714_CR31","doi-asserted-by":"crossref","unstructured":"Xu, D., Yu, X., Jamali, V., Ng, D.W.K., & Schober, R. (2021). Resource allocation for large irs-assisted swipt systems with non-linear energy harvesting model. In: 2021 IEEE Wireless Communications and Networking Conference (WCNC), pp. 1\u20137. IEEE.","DOI":"10.1109\/WCNC49053.2021.9417357"},{"key":"11714_CR32","doi-asserted-by":"crossref","unstructured":"Peng, H., Wang, L.-C., Li, G.Y., & Tsai, A.-H. (2022). Long-lasting uav-aided ris communications based on swipt. In: 2022 IEEE Wireless Communications and Networking Conference (WCNC), pp. 1844\u20131849. IEEE","DOI":"10.1109\/WCNC51071.2022.9771999"},{"key":"11714_CR33","doi-asserted-by":"publisher","first-page":"29614","DOI":"10.1109\/ACCESS.2023.3261547","volume":"11","author":"B Rana","year":"2023","unstructured":"Rana, B., Cho, S.-S., & Hong, I.-P. (2023). Review paper on hardware of reconfigurable intelligent surfaces. IEEE Access, 11, 29614\u201329634.","journal-title":"IEEE Access"},{"issue":"7","key":"11714_CR34","doi-asserted-by":"publisher","first-page":"2042","DOI":"10.1109\/JSAC.2020.3041401","volume":"39","author":"X Liu","year":"2020","unstructured":"Liu, X., Liu, Y., & Chen, Y. (2020). Machine learning empowered trajectory and passive beamforming design in UAV-RIS wireless networks. IEEE Journal on Selected Areas in Communications, 39(7), 2042\u20132055.","journal-title":"IEEE Journal on Selected Areas in Communications"},{"issue":"3","key":"11714_CR35","doi-asserted-by":"publisher","first-page":"3020","DOI":"10.1109\/TVT.2022.3143839","volume":"71","author":"H Mei","year":"2022","unstructured":"Mei, H., Yang, K., Liu, Q., & Wang, K. (2022). 3d-trajectory and phase-shift design for RIS-assisted UAV systems using deep reinforcement learning. IEEE Transactions on Vehicular Technology, 71(3), 3020\u20133029.","journal-title":"IEEE Transactions on Vehicular Technology"},{"issue":"3","key":"11714_CR36","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TWC.2021.3107306","volume":"21","author":"A Khalili","year":"2021","unstructured":"Khalili, A., Monfared, E. M., Zargari, S., Javan, M. R., Yamchi, N. M., & Jorswieck, E. A. (2021). Resource management for transmit power minimization in UAV-assisted RIS hetnets supported by dual connectivity. IEEE Transactions on Wireless Communications, 21(3), 1806\u20131822.","journal-title":"IEEE Transactions on Wireless Communications"},{"issue":"10","key":"11714_CR37","doi-asserted-by":"publisher","first-page":"6826","DOI":"10.1109\/TWC.2023.3245820","volume":"22","author":"H Peng","year":"2023","unstructured":"Peng, H., & Wang, L.-C. (2023). energy harvesting reconfigurable intelligent surface for UAV based on robust deep reinforcement learning. IEEE Transactions on Wireless Communications, 22(10), 6826\u20136838. https:\/\/doi.org\/10.1109\/TWC.2023.3245820","journal-title":"IEEE Transactions on Wireless Communications"},{"issue":"1","key":"11714_CR38","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1109\/TGCN.2022.3201190","volume":"7","author":"K Ntontin","year":"2022","unstructured":"Ntontin, K., Boulogeorgos, A.-A.A., Bj\u00f6rnson, E., Martins, W. A., Kisseleff, S., Abadal, S., Alarc\u00f3n, E., Papazafeiropoulos, A., Lazarakis, F. I., & Chatzinotas, S. (2022). Wireless energy harvesting for autonomous reconfigurable intelligent surfaces. IEEE Transactions on Green Communications and Networking, 7(1), 114\u2013129.","journal-title":"IEEE Transactions on Green Communications and Networking"},{"issue":"3","key":"11714_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3626566","volume":"56","author":"X Xia","year":"2023","unstructured":"Xia, X., Fattah, S. M. M., & Babar, M. A. (2023). A survey on UAV-enabled edge computing: Resource management perspective. ACM Computing Surveys, 56(3), 1\u201336.","journal-title":"ACM Computing Surveys"},{"issue":"1","key":"11714_CR40","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1109\/TWC.2013.112513.130760","volume":"13","author":"H Ju","year":"2013","unstructured":"Ju, H., & Zhang, R. (2013). Throughput maximization in wireless powered communication networks. IEEE Transactions on Wireless Communications, 13(1), 418\u2013428.","journal-title":"IEEE Transactions on Wireless Communications"},{"key":"11714_CR41","doi-asserted-by":"crossref","unstructured":"Tang, Y., Ma, G., Xie, H., Xu, J., & Han, X. (2020). Joint transmit and reflective beamforming design for irs-assisted multiuser miso swipt systems. In: ICC 2020-2020 IEEE International Conference on Communications (ICC), pp. 1\u20136. IEEE","DOI":"10.1109\/ICC40277.2020.9148892"},{"issue":"6","key":"11714_CR42","doi-asserted-by":"publisher","first-page":"3949","DOI":"10.1109\/TWC.2016.2531652","volume":"15","author":"M Mozaffari","year":"2016","unstructured":"Mozaffari, M., Saad, W., Bennis, M., & Debbah, M. (2016). Unmanned aerial vehicle with underlaid device-to-device communications: Performance and tradeoffs. IEEE Transactions on Wireless Communications, 15(6), 3949\u20133963.","journal-title":"IEEE Transactions on Wireless Communications"},{"key":"11714_CR43","volume-title":"Finding Groups in Data: an Introduction to Cluster Analysis","author":"L Kaufman","year":"2009","unstructured":"Kaufman, L., & Rousseeuw, P. J. (2009). Finding Groups in Data: an Introduction to Cluster Analysis. Hoboken: John Wiley & Sons."},{"issue":"5","key":"11714_CR44","doi-asserted-by":"publisher","first-page":"12828","DOI":"10.1111\/exsy.12828","volume":"39","author":"D Mandloi","year":"2022","unstructured":"Mandloi, D., & Arya, R. (2022). Seamless connectivity with 5g enabled unmanned aerial vehicles base stations using machine programming approach. Expert Systems, 39(5), 12828.","journal-title":"Expert Systems"},{"key":"11714_CR45","unstructured":"Lockwood, O., & Qian, M. (2021). Replicating softmax deep double deterministic policy gradients"},{"issue":"4","key":"11714_CR46","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1512\/iumj.1957.6.56038","volume":"6","author":"R Bellman","year":"1957","unstructured":"Bellman, R. (1957). A Markovian decision process. Indiana University Mathematics Journal, 6(4), 679\u2013684. https:\/\/doi.org\/10.1512\/iumj.1957.6.56038","journal-title":"Indiana University Mathematics Journal"},{"key":"11714_CR47","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C. J., & Dayan, P. (1992). Q-learning. Machine Learning, 8, 279\u2013292.","journal-title":"Machine Learning"},{"key":"11714_CR48","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., & Riedmiller, M. (2014). Deterministic policy gradient algorithms. In: International Conference on Machine Learning, pp. 387\u2013395. Pmlr"},{"key":"11714_CR49","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971"},{"key":"11714_CR50","unstructured":"Stekolshchik, R. (2020). Noise, overestimation and exploration in deep reinforcement learning. arXiv preprint arXiv:2006.1416725."},{"key":"11714_CR51","unstructured":"Fujimoto, S., Hoof, H., & Meger, D. (2018). Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596. PMLR."},{"key":"11714_CR52","unstructured":"Hasselt, H. (2010). Double q-learning. Advances in neural information processing systems 23."},{"key":"11714_CR53","first-page":"11767","volume":"33","author":"L Pan","year":"2020","unstructured":"Pan, L., Cai, Q., & Huang, L. (2020). Softmax deep double deterministic policy gradients. Advances in Neural Information Processing Systems, 33, 11767\u201311777.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"11714_CR54","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347"},{"key":"11714_CR55","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., & Moritz, P. (2015). Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR"},{"key":"11714_CR56","doi-asserted-by":"crossref","unstructured":"Qi, C., Wu, C., Lei, L., Li, X., & Cong, P. (2022). Uav path planning based on the improved ppo algorithm. In: 2022 Asia Conference on Advanced Robotics, Automation, and Control Engineering (ARACE), pp. 193\u2013199. IEEE","DOI":"10.1109\/ARACE56528.2022.00040"}],"container-title":["Wireless Personal Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-024-11714-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11277-024-11714-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-024-11714-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T11:11:11Z","timestamp":1736421071000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11277-024-11714-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":56,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["11714"],"URL":"https:\/\/doi.org\/10.1007\/s11277-024-11714-y","relation":{},"ISSN":["0929-6212","1572-834X"],"issn-type":[{"value":"0929-6212","type":"print"},{"value":"1572-834X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"14 December 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not Applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not Applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}]}}