{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T04:08:55Z","timestamp":1750392535153,"version":"3.41.0"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031939297","type":"print"},{"value":"9783031939303","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\/978-3-031-93930-3_5","type":"book-chapter","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T15:26:48Z","timestamp":1750346808000},"page":"77-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Quantifying Uncertainty in\u00a0Complex Reinforcement Learning Scenarios"],"prefix":"10.1007","author":[{"given":"Saeid","family":"Rezaei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2662-6875","authenticated-orcid":false,"given":"Kenneth N.","family":"Brown","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"5_CR1","unstructured":"Dulac-Arnold, G., et al.: An empirical investigation of the challenges of real-world reinforcement learning. arXiv preprint arXiv:2003.11881 (2021)"},{"key":"5_CR2","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"2014","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, Hoboken (2014)"},{"key":"5_CR3","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"5_CR4","unstructured":"Afshar, R.R., Zhang, Y., Vanschoren, J., Kaymak, U.: Automated reinforcement learning: an overview. arXiv preprint arXiv:2201.05000 (2022)"},{"key":"5_CR5","unstructured":"Franke, J.K.H., K\u00f6hler, G., Biedenkapp, A., Hutter, F.: Sample-efficient automated deep reinforcement learning. arXiv preprint arXiv:2009.01555 (2021)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Liu, K., Fu, Y., Wu, L., Li, X., Aggarwal, C., Xiong, H.: Automated feature selection: a reinforcement learning perspective. IEEE Trans. Knowl. Data Eng. (2021)","DOI":"10.1109\/TKDE.2021.3115477"},{"key":"5_CR7","unstructured":"Taitler, A., et al.: pyRDDLGym: from RDDL to gym environments. arXiv preprint arXiv:2211.05939 (2023)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Vamplew, P., et al.: Scalar reward is not enough: a response to Silver, Singh, Precup, and Sutton (2021). Auton. Agents Multi-Agent Syst. 36(2), 41 (2022)","DOI":"10.1007\/s10458-022-09575-5"},{"key":"5_CR9","unstructured":"V\u00e1zquez-Canteli, J.R., Dey, S., Henze, G., Nagy, Z.: CityLearn: standardizing research in multi-agent reinforcement learning for demand response and urban energy management. arXiv preprint arXiv:2012.10504 (2020)"},{"key":"5_CR10","unstructured":"Liu, X.-Y., et al.: FinRL: a deep reinforcement learning library for automated stock trading in quantitative finance. arXiv preprint arXiv:2011.09607 (2022)"},{"key":"5_CR11","unstructured":"Osband, I., Blundell, C., Pritzel, A., Van Roy, B.: Deep exploration via bootstrapped DQN. In: Advances in Neural Information Processing Systems (2016)"},{"key":"5_CR12","unstructured":"Hester, T., Stone, P.: Learning from Delays. Robotics (2013)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Covington, P., Adams, J., Sargin, E.: Deep neural networks for YouTube recommendations. In: Proceedings of the 10th ACM Conference on Recommender Systems, pp. 191\u2013198 (2016)","DOI":"10.1145\/2959100.2959190"},{"key":"5_CR14","unstructured":"Dalal, G., et al.: Safe exploration in continuous action spaces. arXiv preprint arXiv:1801.08757 (2018)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature (2015)","DOI":"10.1038\/nature14236"},{"key":"5_CR16","unstructured":"Abdolmaleki, A., Price, B., Lau, N., Reis, L.P., Neumann, G.: A generalized algorithm for multi-objective reinforcement learning and policy adaptation. In: NeurIPS (2020)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature (2016)","DOI":"10.1038\/nature16961"},{"key":"5_CR18","unstructured":"Agrawal, P., Nair, A., Abbeel, P., Malik, J., Levine, S.: Benchmarking reinforcement learning algorithms on real-world robots. In: Conference on Robot Learning, pp. 361\u2013372 (2019)"},{"key":"5_CR19","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1613\/jair.1.13596","volume":"74","author":"J Parker-Holder","year":"2022","unstructured":"Parker-Holder, J., et al.: Automated reinforcement learning (AutoRL): a survey and open problems. J. Artif. Intell. Res. 74, 517\u2013568 (2022)","journal-title":"J. Artif. Intell. Res."},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Mussi, M., Lombarda, D., Metelli, A.M., Trov\u00f2, F., Restelli, M.: ARLO: a framework for automated reinforcement learning. Expert Syst. Appl. 224, 119883 (2023)","DOI":"10.1016\/j.eswa.2023.119883"},{"issue":"3","key":"5_CR21","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s10994-021-05946-3","volume":"110","author":"E H\u00fcllermeier","year":"2021","unstructured":"H\u00fcllermeier, E., Waegeman, W.: Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods. Mach. Learn. 110(3), 457\u2013506 (2021)","journal-title":"Mach. Learn."},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Majeed, S.J., Hutter, M.: On Q-learning convergence for non-Markov decision processes. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI), pp. 2546\u20132552 (2018)","DOI":"10.24963\/ijcai.2018\/353"},{"key":"5_CR23","unstructured":"Melo, F.A., Ribeiro, M.I., Norte, I.T.: Convergence results for reinforcement learning with partial observability. Institute for Systems and Robotics, Technical report RT-602-05 (2005)"}],"container-title":["Lecture Notes in Computer Science","Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-93930-3_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T15:27:03Z","timestamp":1750346823000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-93930-3_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031939297","9783031939303"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-93930-3_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"20 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EUMAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dublin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ireland","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":"27 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eumas2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/euramas.github.io\/eumas2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}