{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T06:52:55Z","timestamp":1743058375776,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031434266"},{"type":"electronic","value":"9783031434273"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43427-3_18","type":"book-chapter","created":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T21:01:41Z","timestamp":1694898101000},"page":"295-311","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Continual Model-Based Reinforcement Learning for\u00a0Data Efficient Wireless Network Optimisation"],"prefix":"10.1007","author":[{"given":"Cengis","family":"Hasan","sequence":"first","affiliation":[]},{"given":"Alexandros","family":"Agapitos","sequence":"additional","affiliation":[]},{"given":"David","family":"Lynch","sequence":"additional","affiliation":[]},{"given":"Alberto","family":"Castagna","sequence":"additional","affiliation":[]},{"given":"Giorgio","family":"Cruciata","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Aleksandar","family":"Milenovic","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,17]]},"reference":[{"issue":"4","key":"18_CR1","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1109\/TCCN.2019.2933420","volume":"5","author":"E Balevi","year":"2019","unstructured":"Balevi, E., Andrews, J.G.: Online antenna tuning in heterogeneous cellular networks with deep reinforcement learning. IEEE Trans. Cogn. Commun. Netw. 5(4), 1113\u20131124 (2019). https:\/\/doi.org\/10.1109\/TCCN.2019.2933420","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"18_CR2","doi-asserted-by":"publisher","unstructured":"Biza, K., Tsamardinos, I., Triantafillou, S.: Out-of-sample tuning for causal discovery. IEEE Trans. Neural Netw. Learn. Syst. 1\u201311 (2022). https:\/\/doi.org\/10.1109\/TNNLS.2022.3185842","DOI":"10.1109\/TNNLS.2022.3185842"},{"key":"18_CR3","doi-asserted-by":"publisher","unstructured":"Bothe, S., Masood, U., Farooq, H., Imran, A.: Neuromorphic AI empowered root cause analysis of faults in emerging networks. In: IEEE International Black Sea Conference on Communications and Networking, BlackSeaCom 2020, Odessa, Ukraine, 26\u201329 May 2020. pp. 1\u20136. IEEE (2020). https:\/\/doi.org\/10.1109\/BlackSeaCom48709.2020.9235002","DOI":"10.1109\/BlackSeaCom48709.2020.9235002"},{"key":"18_CR4","unstructured":"Bouton, M., Farooq, H., Forgeat, J., Bothe, S., Shirazipour, M., Karlsson, P.: Coordinated reinforcement learning for optimizing mobile networks (Sep 2021)"},{"key":"18_CR5","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1109\/MCOM.2018.1701031","volume":"56","author":"FD Calabrese","year":"2018","unstructured":"Calabrese, F.D., Wang, L., Ghadimi, E., Peters, G., Hanzo, L., Soldati, P.: Learning radio resource management in rans: Framework, opportunities, and challenges. IEEE Commun. Mag. 56, 138\u2013145 (2018)","journal-title":"IEEE Commun. Mag."},{"key":"18_CR6","unstructured":"Chua, K., Calandra, R., McAllister, R., Levine, S.: Deep reinforcement learning in a handful of trials using probabilistic dynamics models. In: Advances in Neural Information Processing Systems 31 (2018)"},{"issue":"1","key":"18_CR7","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1214\/11-AOS940","volume":"40","author":"D Colombo","year":"2012","unstructured":"Colombo, D., Maathuis, M.H., Kalisch, M., Richardson, T.S.: Learning high-dimensional directed acyclic graphs with latent and selection variables. Ann. Stat. 40(1), 294\u2013321 (2012)","journal-title":"Ann. Stat."},{"issue":"1","key":"18_CR8","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/s11277-016-3849-9","volume":"92","author":"N Dandanov","year":"2017","unstructured":"Dandanov, N., Al-Shatri, H., Klein, A., Poulkov, V.: Dynamic self-optimization of the antenna tilt for best trade-off between coverage and capacity in mobile networks. Wirel. Pers. Commun. 92(1), 251\u2013278 (2017). https:\/\/doi.org\/10.1007\/s11277-016-3849-9","journal-title":"Wirel. Pers. Commun."},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Devin, C., Gupta, A., Darrell, T., Abbeel, P., Levine, S.: Learning modular neural network policies for multi-task and multi-robot transfer. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 2169\u20132176. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Eckhardt, H., Klein, S., Gruber, M.: Vertical antenna tilt optimization for lte base stations. In: VTC Spring, pp. 1\u20135. IEEE (2011). http:\/\/dblp.uni-trier.de\/db\/conf\/vtc\/vtc2011s.html#EckhardtKG11","DOI":"10.1109\/VETECS.2011.5956370"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Eisenbl\u00e4tter, A., Geerdes, H.: Capacity optimization for UMTS: bounds and benchmarks for interference reduction. In: Proceedings of the IEEE 19th International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2008, 15\u201318 September 2008, Cannes, French Riviera, France, pp. 1\u20136. IEEE (2008). https:\/\/doi.org\/10.1109\/PIMRC.2008.4699919","DOI":"10.1109\/PIMRC.2008.4699919"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Isele, D., Cosgun, A.: Selective experience replay for lifelong learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"18_CR13","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1613\/jair.1.13673","volume":"75","author":"K Khetarpal","year":"2020","unstructured":"Khetarpal, K., Riemer, M., Rish, I., Precup, D.: Towards continual reinforcement learning: a review and perspectives. J. Artif. Intell. Res. 75, 1401\u20131476 (2020)","journal-title":"J. Artif. Intell. Res."},{"issue":"13","key":"18_CR14","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521\u20133526 (2017)","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"12","key":"18_CR15","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","volume":"40","author":"Z Li","year":"2017","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935\u20132947 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR16","unstructured":"Mendez, J.A., van Seijen, H., Eaton, E.: Modular lifelong reinforcement learning via neural composition. arXiv preprint arXiv:2207.00429 (2022)"},{"issue":"10","key":"18_CR17","doi-asserted-by":"publisher","first-page":"2239","DOI":"10.1109\/JSAC.2019.2933973","volume":"37","author":"YS Nasir","year":"2019","unstructured":"Nasir, Y.S., Guo, D.: Multi-agent deep reinforcement learning for dynamic power allocation in wireless networks. IEEE J. Sel. Areas Commun. 37(10), 2239\u20132250 (2019). https:\/\/doi.org\/10.1109\/JSAC.2019.2933973","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"18_CR18","unstructured":"Ogarrio, J.M., Spirtes, P., Ramsey, J.: A hybrid causal search algorithm for latent variable models. In: Proceedings of the Eighth International Conference on Probabilistic Graphical Models, 06\u201309 Sep, vol. 52, pp. 368\u2013379. PMLR (2016)"},{"issue":"1","key":"18_CR19","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1109\/TNET.2013.2294965","volume":"23","author":"B Partov","year":"2015","unstructured":"Partov, B., Leith, D.J., Razavi, R.: Utility fair optimization of antenna tilt angles in lte networks. IEEE\/ACM Trans. Netw. 23(1), 175\u2013185 (2015). https:\/\/doi.org\/10.1109\/TNET.2013.2294965","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"18_CR20","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s41060-018-0104-3","volume":"6","author":"VK Raghu","year":"2018","unstructured":"Raghu, V.K., et al.: Comparison of strategies for scalable causal discovery of latent variable models from mixed data. Inter. J. Data Sci. Anal. 6, 33\u201345 (2018)","journal-title":"Inter. J. Data Sci. Anal."},{"key":"18_CR21","unstructured":"Rolnick, D., Ahuja, A., Schwarz, J., Lillicrap, T., Wayne, G.: Experience replay for continual learning. In: Advances in Neural Information Processing Systems 32 (2019)"},{"key":"18_CR22","unstructured":"Rusu, A.A., et al.: Policy distillation. arXiv preprint arXiv:1511.06295 (2015)"},{"key":"18_CR23","unstructured":"Rusu, A.A., et al.: Progressive neural networks. arXiv preprint arXiv:1606.04671 (2016)"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Saini, S.K., Dhamnani, S., Ibrahim, A.A., Chavan, P.: Multiple treatment effect estimation using deep generative model with task embedding. In: The World Wide Web Conference, pp. 1601\u20131611 (2019)","DOI":"10.1145\/3308558.3313744"},{"key":"18_CR25","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"18_CR26","unstructured":"Schwarz, J., et al.: Progress & Compress: A scalable framework for continual learning. In: International Conference on Machine Learning, pp. 4528\u20134537. PMLR (2018)"},{"issue":"6","key":"18_CR27","doi-asserted-by":"publisher","first-page":"4038","DOI":"10.1109\/TWC.2020.2979446","volume":"19","author":"RSB Shafin","year":"2020","unstructured":"Shafin, R.S.B., et al.: Self-tuning sectorization: deep reinforcement learning meets broadcast beam optimization. IEEE Trans. Wirel. Commun. 19(6), 4038\u20134053 (2020). https:\/\/doi.org\/10.1109\/TWC.2020.2979446","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"18_CR28","unstructured":"Shi, C., Blei, D., Veitch, V.: Adapting Neural Networks for the Estimation of Treatment Effects. In: Advances in Neural Information Processing Systems 32 (2019)"},{"key":"18_CR29","unstructured":"Traor\u00e9, Ret al.: Discorl: continual reinforcement learning via policy distillation. arXiv preprint arXiv:1907.05855 (2019)"},{"key":"18_CR30","doi-asserted-by":"publisher","unstructured":"Vannella, F., Jeong, J., Prouti\u00e8re, A.: Off-policy learning for remote electrical tilt optimization. In: 92nd IEEE Vehicular Technology Conference, VTC Fall 2020, Victoria, BC, Canada, 18 November -16 December 2020. pp. 1\u20135. IEEE (2020). https:\/\/doi.org\/10.1109\/VTC2020-Fall49728.2020.9348456","DOI":"10.1109\/VTC2020-Fall49728.2020.9348456"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Yin, H., Pan, S.J.: Knowledge transfer for deep reinforcement learning with hierarchical experience replay. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10733"},{"key":"18_CR32","unstructured":"Yoon, J., Yang, E., Lee, J., Hwang, S.J.: Lifelong learning with dynamically expandable networks. arXiv preprint arXiv:1708.01547 (2017)"},{"key":"18_CR33","doi-asserted-by":"publisher","unstructured":"Zhao, W., Queralta, J.P., Westerlund, T.: Sim-to-real transfer in deep reinforcement learning for robotics: a survey. In: 2020 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 737\u2013744 (2020).https:\/\/doi.org\/10.1109\/SSCI47803.2020.9308468","DOI":"10.1109\/SSCI47803.2020.9308468"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43427-3_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T21:03:47Z","timestamp":1694898227000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43427-3_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434266","9783031434273"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43427-3_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"17 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"829","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"196","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.63","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted papers.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}