{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T19:07:45Z","timestamp":1754161665390,"version":"3.41.2"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031952951"},{"type":"electronic","value":"9783031952968"}],"license":[{"start":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T00:00:00Z","timestamp":1753833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T00:00:00Z","timestamp":1753833600000},"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":[[2026]]},"DOI":"10.1007\/978-3-031-95296-8_18","type":"book-chapter","created":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T05:16:11Z","timestamp":1753766171000},"page":"196-202","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty-Based Dynamic Weighted Experience Replay for\u00a0Human-in-the-Loop Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2655-2992","authenticated-orcid":false,"given":"Roman","family":"Pantin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4993-3285","authenticated-orcid":false,"given":"Shavkat","family":"Mamarajabov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,30]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Boularias, A., Chaib-draa, B.: Apprenticeship learning via soft local homomorphisms. In: 2010 IEEE International Conference on Robotics and Automation, pp. 2971\u20132976 (2010). https:\/\/doi.org\/10.1109\/ROBOT.2010.5509717","DOI":"10.1109\/ROBOT.2010.5509717"},{"key":"18_CR2","doi-asserted-by":"publisher","unstructured":"Durmanov, A., Karakulov, F., Yunusova, R., Vorobeva, O., Kaldibayev, N., Aripova, A.: Accounting for organizational and economic mechanisms in greenhouse activities. WSEAS Trans. Environ. Dev. 20, 242\u2013255 (2024). https:\/\/doi.org\/10.37394\/232015.2024.20.25","DOI":"10.37394\/232015.2024.20.25"},{"key":"18_CR3","doi-asserted-by":"publisher","first-page":"3642","DOI":"10.1109\/LRA.2020.2979656","volume":"5","author":"S Gangapurwala","year":"2020","unstructured":"Gangapurwala, S., Mitchell, A.L., Havoutis, I.: Guided constrained policy optimization for dynamic quadrupedal robot locomotion. IEEE Robot. Autom. Lett. 5, 3642\u20133649 (2020). https:\/\/doi.org\/10.1109\/LRA.2020.2979656","journal-title":"IEEE Robot. Autom. Lett."},{"key":"18_CR4","doi-asserted-by":"publisher","unstructured":"Hou, Y., Li, X., Wang, H., Yunusova, R.: Focusing on energy efficiency: the convergence of green financing, fintech, financial inclusion, and natural resource rents for a greener Asia. Resour. Policy 93 (2024). https:\/\/doi.org\/10.1016\/j.resourpol.2024.105052","DOI":"10.1016\/j.resourpol.2024.105052"},{"key":"18_CR5","doi-asserted-by":"publisher","unstructured":"Khababa, N., Yunusova, R.: Supply chain operations risk management, resilience, and information technology integration on operations performance: Does demand forecasting matters. Oper. Res. Eng. Sci. Theory Appl. 7(2), 85\u2013106 (2024). https:\/\/doi.org\/10.31181\/oresta\/070205","DOI":"10.31181\/oresta\/070205"},{"key":"18_CR6","unstructured":"Liu, Z., et al.: Constrained variational policy optimization for safe reinforcement learning. arXiv abs\/2201.11927 (2022)"},{"key":"18_CR7","doi-asserted-by":"publisher","unstructured":"MacGlashan, J., et al.: Interactive learning from policy-dependent human feedback. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 2285\u20132294 (2017). https:\/\/doi.org\/10.48550\/arXiv.1701.06049","DOI":"10.48550\/arXiv.1701.06049"},{"key":"18_CR8","unstructured":"Mhamed, J., Gu, S.: SCPO: safe reinforcement learning with safety critic policy optimization. In: arXiv, vol. abs\/2311.00880 (2023)"},{"key":"18_CR9","doi-asserted-by":"publisher","unstructured":"Muthuswamy, V., Yunusova, R.: Corporate social responsibility disclosure and bankruptcy financial risks: moderating role of corporate governance index. Cuadernos de Economia 46(132), 69\u201378 (2023). https:\/\/doi.org\/10.32826\/cude.v46i132.1207","DOI":"10.32826\/cude.v46i132.1207"},{"key":"18_CR10","doi-asserted-by":"publisher","unstructured":"Nguyen, H., Garratt, M., Bui, L., Abbass, H.: Apprenticeship learning for continuous state spaces and actions in a swarm-guidance shepherding task. In: 2019 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 102\u2013109 (2019). https:\/\/doi.org\/10.1109\/SSCI44817.2019.9002756","DOI":"10.1109\/SSCI44817.2019.9002756"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Pantin, R.: Developing a dynamic decision-support framework for higher education management systems through real-time information extraction. In: ACM International Conference Proceeding Series, pp. 497\u2013502 (2023). https:\/\/doi.org\/10.1145\/3644713.3644786","DOI":"10.1145\/3644713.3644786"},{"key":"18_CR12","doi-asserted-by":"publisher","unstructured":"Ram\u00edrez, J., Yu, W.: Safe exploration in reinforcement learning for learning from human experts. In: 2023 IEEE International Conference on Artificial Intelligence, Blockchain, and Internet of Things (AIBThings), pp.\u00a01\u20135 (2023). https:\/\/doi.org\/10.1109\/AIBThings58340.2023.10292489","DOI":"10.1109\/AIBThings58340.2023.10292489"},{"key":"18_CR13","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1146\/annurev-control-100819-063206","volume":"3","author":"H Ravichandar","year":"2020","unstructured":"Ravichandar, H., Polydoros, A.S., Chernova, S., Billard, A.: Recent advances in robot learning from demonstration. Annu. Rev. Control Robot. Auton. Syst. 3, 297\u2013330 (2020). https:\/\/doi.org\/10.1146\/annurev-control-100819-063206","journal-title":"Annu. Rev. Control Robot. Auton. Syst."},{"key":"18_CR14","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1613\/jair.1.15348","volume":"79","author":"C Retzlaff","year":"2024","unstructured":"Retzlaff, C., Das, S., Wayllace, C., Mousavi, P., Afshari, M., Yang, T., et al.: Human-in-the-loop reinforcement learning: a survey and position on requirements, challenges, and opportunities. J. Artif. Intell. Res. 79, 359\u2013415 (2024). https:\/\/doi.org\/10.1613\/jair.1.15348","journal-title":"J. Artif. Intell. Res."},{"key":"18_CR15","doi-asserted-by":"publisher","first-page":"3123","DOI":"10.1109\/tac.2020.3015931","volume":"66","author":"M Wen","year":"2020","unstructured":"Wen, M., Topcu, U.: Constrained cross-entropy method for safe reinforcement learning. IEEE Trans. Autom. Control 66, 3123\u20133137 (2020). https:\/\/doi.org\/10.1109\/tac.2020.3015931","journal-title":"IEEE Trans. Autom. Control"},{"issue":"1","key":"18_CR16","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1109\/TNNLS.2022.3177685","volume":"35","author":"J Wu","year":"2022","unstructured":"Wu, J., Huang, Z., Huang, W., Lv, C.: Prioritized experience-based reinforcement learning with human guidance for autonomous driving. IEEE Trans. Neural Netw. Learn. Syst. 35(1), 855\u2013869 (2022). https:\/\/doi.org\/10.1109\/TNNLS.2022.3177685","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"18_CR17","doi-asserted-by":"publisher","unstructured":"Yunusova, R.: Decentralized blockchain networks and economic security: balancing scalability and security tradeoffs. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics). LNCS, vol. 14542, pp. 244\u2013252 (2024). https:\/\/doi.org\/10.1007\/978-3-031-60994-7_20","DOI":"10.1007\/978-3-031-60994-7_20"},{"key":"18_CR18","doi-asserted-by":"publisher","first-page":"17","DOI":"10.3390\/robotics7020017","volume":"7","author":"Z Zhu","year":"2018","unstructured":"Zhu, Z., Hu, H.: Robot learning from demonstration in robotic assembly: a survey. Robotics 7, 17 (2018). https:\/\/doi.org\/10.3390\/robotics7020017","journal-title":"Robotics"}],"container-title":["Lecture Notes in Computer Science","Internet of Things, Smart Spaces, and Next Generation Networks and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-95296-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T05:16:13Z","timestamp":1753766173000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-95296-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,30]]},"ISBN":["9783031952951","9783031952968"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-95296-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,7,30]]},"assertion":[{"value":"30 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ruSMART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Conference on Internet of Things and Smart Spaces","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"rusmart2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/new2an.info\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}