{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:31:08Z","timestamp":1772119868393,"version":"3.50.1"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":[[2025,11]]},"DOI":"10.1007\/s11277-025-11845-w","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T14:35:48Z","timestamp":1762871748000},"page":"93-111","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning Based Approach for Underwater Environment to Evaluate Agent Algorithm"],"prefix":"10.1007","volume":"145","author":[{"given":"K. R.","family":"Shruthi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"Kavitha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"11845_CR1","doi-asserted-by":"crossref","unstructured":"Shruthi, K. R., & Dr. Kavitha, C. (2022). Reinforcement learning-based approach for establishing energy-efficient routes in underwater sensor networks, 8th International Conference on Electronics, Computing and Communication Technologies, IEEE CONECCT-2022.","DOI":"10.1109\/CONECCT55679.2022.9865724"},{"key":"11845_CR2","unstructured":"Shruthi, K. R. (2019). An Artificial Intelligence Based Routing for Underwater Wireless Sensor Networks, 4th International Conference on Electrical, Electronics, Communication, Computer Technologies, and Optimization Techniques."},{"key":"11845_CR3","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5554791","author":"Q Qin","year":"2021","unstructured":"Qin, Q., Tian, Y., & Wang, X. (2021). Three-dimensional UWSN positioning algorithm based on modified RSSI values. Mobile Information Systems. https:\/\/doi.org\/10.1155\/2021\/5554791","journal-title":"Mobile Information Systems"},{"key":"11845_CR4","doi-asserted-by":"publisher","unstructured":"Bouk, S. H., Ahmed, S. H., & Kim, D. (2016). Delay tolerance in underwater wireless communications: A routing perspective. Mobile Information Systems, 9. https:\/\/doi.org\/10.1155\/2016\/6574697","DOI":"10.1155\/2016\/6574697"},{"issue":"1","key":"11845_CR5","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/COMST.2017.2768802","volume":"20","author":"S Jiang","year":"2018","unstructured":"Jiang, S. (2018). State-of-the-art medium access control (MAC) protocols for underwater acoustic networks: A survey based on a MAC reference model. IEEE Communications Surveys and Tutorials, 20(1), 96\u2013131.","journal-title":"IEEE Communications Surveys and Tutorials"},{"key":"11845_CR6","doi-asserted-by":"publisher","unstructured":"Hu, T., & Fei, Y. (2010). An Adaptive and Energy-efficient Routing Protocol Based on Machine Learning for Underwater Delay Tolerant Networks, 2010 IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, pp. 381\u2013384. https:\/\/doi.org\/10.1109\/MASCOTS.2010.45","DOI":"10.1109\/MASCOTS.2010.45"},{"key":"11845_CR7","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s10723-022-09636-9","volume":"20","author":"W Zhang","year":"2022","unstructured":"Zhang, W., Li, J., Wan, Y., et al. (2022). Machine Learning-Based Performance-Efficient MAC protocol for single hop underwater acoustic sensor networks. J Grid Computing, 20, 41. https:\/\/doi.org\/10.1007\/s10723-022-09636-9","journal-title":"J Grid Computing"},{"key":"11845_CR8","doi-asserted-by":"publisher","unstructured":"Varshini Vidyadhar, Nagaraj, R., & Ashoka, D. V. (2021). NetAI-Gym: Customized environment for network to evaluate agent algorithm using reinforcement learning in Open-AI gym platform. International Journal of Advanced Computer Science and Applications(IJACSA), 12(4). https:\/\/doi.org\/10.14569\/IJACSA.2021.0120423","DOI":"10.14569\/IJACSA.2021.0120423"},{"issue":"54","key":"11845_CR9","first-page":"1","volume":"20","author":"M H\u00fcttenrauch","year":"2018","unstructured":"H\u00fcttenrauch, M., Adrian, S., & Neumann, G. (2018). Deep reinforcement learning for swarm systems. Journal Of Machine Learning Research, 20(54), 1\u201331.","journal-title":"Journal Of Machine Learning Research"},{"key":"11845_CR10","doi-asserted-by":"publisher","first-page":"1392","DOI":"10.1007\/s11431-015-5848-6","volume":"58","author":"C Sun","year":"2015","unstructured":"Sun, C., & Duan, H. (2015). Markov decision evolutionary game theoretic learning for cooperative sensing of unmanned aerial vehicles. Science China Technological Sciences, 58, 1392\u20131400.","journal-title":"Science China Technological Sciences"},{"issue":"6","key":"11845_CR11","doi-asserted-by":"publisher","DOI":"10.3390\/s20061697","volume":"20","author":"R Ghoul","year":"2020","unstructured":"Ghoul, R., He, J., Djaidja, S., Al-qaness, M. A. A., & Kim, S. (2020). PDTR: Probabilistic and deterministic tree-based routing for wireless sensor networks. Sensors, 20(6), Article 1697.","journal-title":"Sensors"},{"key":"11845_CR12","doi-asserted-by":"publisher","first-page":"1726","DOI":"10.1631\/FITEE.1900533","volume":"21","author":"H Wang","year":"2020","unstructured":"Wang, H., Liu, N., & Zhang, Y. (2020). Deep reinforcement learning: A survey. Front Inform Technol Electron Eng, 21, 1726\u20131744.","journal-title":"Front Inform Technol Electron Eng"},{"key":"11845_CR13","unstructured":"Greg Brockman, V., Cheung, L., Pettersson, J., & Schneider John Schulman, Jie Tang and Wojciech Zaremba, openai gym, arXiv:1606.01540, 2016."},{"key":"11845_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2023.109562","volume":"222","author":"CS Nandyala","year":"2023","unstructured":"Nandyala, C. S., Kim, H. W., & Cho, H. S. (2023). QTAR: A Q-learning-based topology-aware routing protocol for underwater wireless sensor networks. Computer Networks, 222, Article 109562. https:\/\/doi.org\/10.1016\/j.comnet.2023.109562","journal-title":"Computer Networks"},{"key":"11845_CR15","doi-asserted-by":"publisher","unstructured":"Alsalman, L., & Alotaibi, E. (2021). A Balanced Routing Protocol Based on Machine Learning for Underwater Sensor Networks, in IEEE Access, vol. 9, pp. 152082\u2013152097. https:\/\/doi.org\/10.1109\/ACCESS.2021.3126107","DOI":"10.1109\/ACCESS.2021.3126107"},{"key":"11845_CR16","doi-asserted-by":"publisher","unstructured":"Abadi, A. F. E., Asghari, S. A., Marvasti, M. B., Abaei, G., Nabavi, M., & Savaria, Y. (2022). RLBEEP: Reinforcement-Learning-Based Energy Efficient Control and Routing Protocol for Wireless Sensor Networks, in IEEE Access, vol. 10, pp. 44123\u201344135. https:\/\/doi.org\/10.1109\/ACCESS.2022.3167058","DOI":"10.1109\/ACCESS.2022.3167058"},{"issue":"7","key":"11845_CR17","doi-asserted-by":"publisher","first-page":"6807","DOI":"10.1109\/TITS.2021.3062500","volume":"23","author":"J Wu","year":"2022","unstructured":"Wu, J., Song, C., Ma, J., Wu, J., & Han, G. (2022). Reinforcement learning and particle swarm optimization supporting real-time rescue assignments for multiple autonomous underwater vehicles. IEEE Transactions on Intelligent Transportation Systems, 23(7), 6807\u20136820. https:\/\/doi.org\/10.1109\/TITS.2021.3062500","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"11845_CR18","doi-asserted-by":"publisher","first-page":"1570","DOI":"10.1016\/j.adhoc.2022.102953","volume":"136","author":"S Yao","year":"2022","unstructured":"Yao, S., Zheng, M., Han, X., Li, S., & Yin, J. (2022). Adaptive clustering routing protocol for underwater sensor networks. Ad Hoc Networks, 136, 1570\u20138705. https:\/\/doi.org\/10.1016\/j.adhoc.2022.102953","journal-title":"Ad Hoc Networks"},{"key":"11845_CR19","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1007\/s11277-021-08467-3","volume":"120","author":"BS Halakarnimath","year":"2021","unstructured":"Halakarnimath, B. S., & Sutagundar, A. V. (2021). Reinforcement Learning-Based routing in underwater acoustic sensor networks. Wireless Personal Communications, 120, 419\u2013446. https:\/\/doi.org\/10.1007\/s11277-021-08467-3","journal-title":"Wireless Personal Communications"},{"key":"11845_CR20","unstructured":"Brendan, O. D., Osband, I., Munos, R., & Mnih, V. (2018). The uncertainty bellman equation and exploration, arXiv:1709.05380v4 [cs.AI]."},{"key":"11845_CR21","unstructured":"Tim, G. J., Rudner, V. H., Pong, R., McAllister, Y., Gal, S., & Levine (2021). Outcome-Driven Reinforcement Learning via Variational Inference, 35th Conference on Neural Information Processing SystemsNeurIPS."},{"key":"11845_CR22","doi-asserted-by":"publisher","first-page":"541","DOI":"10.12785\/ijcds\/110144","volume":"11","author":"AB G, Paavai","year":"2022","unstructured":"G, Paavai, A. B. (2022). Study of deep reinforcement learning with Epsilon-Greedy exploration. International Journal of Computing and Digital Systems, 11, 541\u2013551. https:\/\/doi.org\/10.12785\/ijcds\/110144","journal-title":"International Journal of Computing and Digital Systems"},{"key":"11845_CR23","doi-asserted-by":"publisher","unstructured":"Igor, C. F., Castro, Eduardo, P. M., C\u00e2mara, Marcos, A. M., Vieira, Luiz, F. M., & Vieira Underwater greedy geographic routing by network Embedding, computer networks, 220, 2023, 109473, ISSN 1389\u2009\u2013\u20091286, https:\/\/doi.org\/10.1016\/j.comnet.2022.109473","DOI":"10.1016\/j.comnet.2022.109473"},{"key":"11845_CR24","doi-asserted-by":"publisher","unstructured":"Haifeng Ling, T., Zhu, W., He, H., Luo, Q., Wang, Y., & Jiang (2020). Coverage Optimization of Sensors under Multiple Constraints Using the Improved PSO Algorithm, Mathematical Problems in Engineering, vol. Article ID 8820907, 10 pages, 2020. https:\/\/doi.org\/10.1155\/2020\/8820907","DOI":"10.1155\/2020\/8820907"},{"key":"11845_CR25","doi-asserted-by":"publisher","unstructured":"Coutinho, R., & Boukerche, A. (2017 pp). Opportunistic Routing in Underwater Sensor Networks: Potentials, Challenges and Guidelines, in 2017 13th International Conference on Distributed Computing in Sensor Systems (DCOSS), Ottawa, ON, Canada, 1\u20132. https:\/\/doi.org\/10.1109\/DCOSS.2017.42","DOI":"10.1109\/DCOSS.2017.42"}],"container-title":["Wireless Personal Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-025-11845-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11277-025-11845-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-025-11845-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T14:59:23Z","timestamp":1764601163000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11277-025-11845-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":25,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["11845"],"URL":"https:\/\/doi.org\/10.1007\/s11277-025-11845-w","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3291459\/v1","asserted-by":"object"}]},"ISSN":["0929-6212","1572-834X"],"issn-type":[{"value":"0929-6212","type":"print"},{"value":"1572-834X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"24 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 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":"Competing Interests"}}]}}