{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T04:10:36Z","timestamp":1748059836478,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609932","type":"print"},{"value":"9789819609949","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-0994-9_13","type":"book-chapter","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T13:23:03Z","timestamp":1748006583000},"page":"137-147","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Navigation in\u00a0Unknown Environment Using Soft Actor-Critic"],"prefix":"10.1007","author":[{"given":"Giovanni","family":"Di Gennaro","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amedeo","family":"Buonanno","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Nogarotto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco A. N.","family":"Palmieri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,24]]},"reference":[{"key":"13_CR1","volume-title":"Reinforcement Learning and Optimal Control","author":"D Bertsekas","year":"2019","unstructured":"Bertsekas, D.: Reinforcement Learning and Optimal Control. Athena Scientific, Belmont, Massachusetts (2019)"},{"key":"13_CR2","doi-asserted-by":"publisher","first-page":"12320","DOI":"10.1007\/s11227-021-03743-2","volume":"77","author":"G Di Gennaro","year":"2021","unstructured":"Di Gennaro, G., Buonanno, A., Palmieri, F.A.N.: Considerations about learning word2vec. J. Supercomput. 77, 12320\u201312335 (2021). https:\/\/doi.org\/10.1007\/s11227-021-03743-2","journal-title":"J. Supercomput."},{"key":"13_CR3","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: Dy, J.G.,\u00a0Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a080, pp. 1582\u20131591. PMLR, Stockholm, Sweden (2018). http:\/\/proceedings.mlr.press\/v80\/fujimoto18a.html"},{"issue":"4","key":"13_CR4","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1109\/TSSC.1969.300225","volume":"5","author":"K Fukushima","year":"1969","unstructured":"Fukushima, K.: Visual feature extraction by a multilayered network of analog threshold elements. IEEE Trans. Syst. Sci. Cybern. 5(4), 322\u2013333 (1969). https:\/\/doi.org\/10.1109\/TSSC.1969.300225","journal-title":"IEEE Trans. Syst. Sci. Cybern."},{"key":"13_CR5","unstructured":"Haarnoja, T., Tang, H., Abbeel, P., Levine, S.: Reinforcement learning with deep energy-based policies. In: Proceedings of the International Conference on Machine Learning (2017). https:\/\/api.semanticscholar.org\/CorpusID:11227891"},{"key":"13_CR6","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In:\u00a0Dy, J.,\u00a0Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, vol.\u00a080, pp. 1861\u20131870. PMLR, Stockholm, Sweden (2018)"},{"key":"13_CR7","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017). arXiv:1412.6980"},{"key":"13_CR8","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes (2022). arXiv:1312.6114"},{"issue":"4","key":"13_CR9","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1016\/0098-1354(92)80051-A","volume":"16","author":"M Kramer","year":"1992","unstructured":"Kramer, M.: Autoassociative neural networks. Comput. Chem. Eng. 16(4), 313\u2013328 (1992). https:\/\/doi.org\/10.1016\/0098-1354(92)80051-A","journal-title":"Comput. Chem. Eng."},{"key":"13_CR10","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436\u2013444 (2015). https:\/\/doi.org\/10.1038\/nature14539","journal-title":"Nature"},{"issue":"4","key":"13_CR11","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/MSP.2020.2973615","volume":"37","author":"Y Li","year":"2020","unstructured":"Li, Y., Ibanez-Guzman, J.: Lidar for autonomous driving: the principles, challenges, and trends for automotive lidar and perception systems. IEEE Signal Process. Mag. 37(4), 50\u201361 (2020). https:\/\/doi.org\/10.1109\/MSP.2020.2973615","journal-title":"IEEE Signal Process. Mag."},{"key":"13_CR12","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning (2013). arXiv:1312.5602"},{"key":"13_CR13","doi-asserted-by":"publisher","first-page":"15193","DOI":"10.1109\/ACCESS.2022.3148127","volume":"10","author":"FAN Palmieri","year":"2022","unstructured":"Palmieri, F.A.N., Pattipati, K.R., Di Gennaro, G., Fioretti, G., Verolla, F., Buonanno, A.: A unifying view of estimation and control using belief propagation with application to path planning. IEEE Access 10, 15193\u201315216 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3148127","journal-title":"IEEE Access"},{"key":"13_CR14","doi-asserted-by":"publisher","unstructured":"Polack, P., Altch\u00e9, F., d\u2019Andr\u00e9a Novel, B., de\u00a0La\u00a0Fortelle, A.: The kinematic bicycle model: a consistent model for planning feasible trajectories for autonomous vehicles? In: Intelligent Vehicles Symposium (IV), pp. 812\u2013818. IEEE, Los Angeles, CA, USA (2017). https:\/\/doi.org\/10.1109\/IVS.2017.7995816","DOI":"10.1109\/IVS.2017.7995816"},{"key":"13_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1433-9","volume-title":"Vehicle Dynamics and Control","author":"R Rajamani","year":"2012","unstructured":"Rajamani, R.: Vehicle Dynamics and Control. Springer, New York, NY (2012)"},{"key":"13_CR16","volume-title":"Reinforcement Learning: An Introduction","author":"R Sutton","year":"2018","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA (2018)"},{"key":"13_CR17","unstructured":"Ziebart, B.D., Maas, A., Bagnell, J.A., Dey, A.K.: Maximum entropy inverse reinforcement learning. In: Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence, pp. 1433\u20131438. AAAI (2008)"}],"container-title":["Smart Innovation, Systems and Technologies","Advanced Neural Artificial Intelligence: Theories and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0994-9_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T13:23:08Z","timestamp":1748006588000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0994-9_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819609932","9789819609949"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0994-9_13","relation":{},"ISSN":["2190-3018","2190-3026"],"issn-type":[{"value":"2190-3018","type":"print"},{"value":"2190-3026","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}