{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T16:47:37Z","timestamp":1758041257536,"version":"3.44.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032045577"},{"type":"electronic","value":"9783032045584"}],"license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"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\/978-3-032-04558-4_28","type":"book-chapter","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:17:11Z","timestamp":1757589431000},"page":"349-360","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating the\u00a0Impact of\u00a0Data Curation on\u00a0Off-Policy Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6647-0732","authenticated-orcid":false,"given":"Matthias","family":"Blum","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5776-6558","authenticated-orcid":false,"given":"Shahram","family":"Eivazi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"28_CR1","doi-asserted-by":"publisher","unstructured":"An, G., Zhang, S.: Pruning replay buffer for efficient training of deep reinforcement learning. J. Emerg. Invest. (2023). https:\/\/doi.org\/10.59720\/23-068","DOI":"10.59720\/23-068"},{"key":"28_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/3-540-49257-7_15","volume-title":"Database Theory \u2014 ICDT\u201999","author":"K Beyer","year":"1999","unstructured":"Beyer, K., Goldstein, J., Ramakrishnan, R., Shaft, U.: When is \u201cnearest neighbor\u2019\u2019 meaningful? In: Beeri, C., Buneman, P. (eds.) ICDT 1999. LNCS, vol. 1540, pp. 217\u2013235. Springer, Heidelberg (1999). https:\/\/doi.org\/10.1007\/3-540-49257-7_15"},{"key":"28_CR3","first-page":"8242","volume":"34","author":"N Bjorck","year":"2021","unstructured":"Bjorck, N., Gomes, C.P., Weinberger, K.Q.: Towards deeper deep reinforcement learning with spectral normalization. Adv. Neural. Inf. Process. Syst. 34, 8242\u20138255 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR4","unstructured":"Brittain, M., Bertram, J., Yang, X., Wei, P.: Prioritized sequence experience replay. arXiv preprint arXiv:1905.12726 (2019)"},{"key":"28_CR5","first-page":"13049","volume":"33","author":"M Dennis","year":"2020","unstructured":"Dennis, M., et al.: Emergent complexity and zero-shot transfer via unsupervised environment design. Adv. Neural. Inf. Process. Syst. 33, 13049\u201313061 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"274","key":"28_CR6","first-page":"1","volume":"23","author":"S Huang","year":"2022","unstructured":"Huang, S., et al.: Cleanrl: high-quality single-file implementations of deep reinforcement learning algorithms. J. Mach. Learn. Res. 23(274), 1\u201318 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Isele, D., Cosgun, A.: Selective experience replay for lifelong learning. In: 32nd Conference on Artificial Intelligence, Proceedings. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, USA, vol. 32, no. 1 (2018)","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"28_CR8","unstructured":"Jones, A.L.: Scaling scaling laws with board games. arXiv preprint arXiv:2104.03113 (2021)"},{"key":"28_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2022.03.003","volume":"85","author":"P Ladosz","year":"2022","unstructured":"Ladosz, P., Weng, L., Kim, M., Oh, H.: Exploration in deep reinforcement learning: a survey. Inf. Fusion 85, 1\u201322 (2022)","journal-title":"Inf. Fusion"},{"key":"28_CR10","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"28_CR11","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1023\/A:1022628806385","volume":"8","author":"LJ Lin","year":"1992","unstructured":"Lin, L.J.: Self-improving reactive agents based on reinforcement learning, planning and teaching. Mach. Learn. 8, 293\u2013321 (1992)","journal-title":"Mach. Learn."},{"key":"28_CR12","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1613\/jair.5699","volume":"61","author":"MC Machado","year":"2018","unstructured":"Machado, M.C., Bellemare, M.G., Talvitie, E., Veness, J., Hausknecht, M., Bowling, M.: Revisiting the arcade learning environment: evaluation protocols and open problems for general agents. J. Artif. Intell. Res. 61, 523\u2013562 (2018)","journal-title":"J. Artif. Intell. Res."},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"issue":"181","key":"28_CR14","first-page":"1","volume":"21","author":"S Narvekar","year":"2020","unstructured":"Narvekar, S., Peng, B., Leonetti, M., Sinapov, J., Taylor, M.E., Stone, P.: Curriculum learning for reinforcement learning domains: a framework and survey. J. Mach. Learn. Res. 21(181), 1\u201350 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR15","unstructured":"Neumann, O., Gros, C.: Scaling laws for a multi-agent reinforcement learning model. arXiv preprint arXiv:2210.00849 (2022)"},{"key":"28_CR16","unstructured":"Ota, K., Jha, D.K., Kanezaki, A.: Training larger networks for deep reinforcement learning. arXiv preprint arXiv:2102.07920 (2021)"},{"key":"28_CR17","first-page":"20596","volume":"34","author":"M Paul","year":"2021","unstructured":"Paul, M., Ganguli, S., Dziugaite, G.K.: Deep learning on a data diet: finding important examples early in training. Adv. Neural. Inf. Process. Syst. 34, 20596\u201320607 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Rojanaarpa, T., Kataeva, I.: Density-based data pruning method for deep reinforcement learning. In: 15th International Conference on Machine Learning and Applications (ICMLA), Proceedings. Proceedings of the IEEE International Conference on Machine Learning and Applications, Anaheim, USA, vol.\u00a015, pp. 266\u2013271 (2016)","DOI":"10.1109\/ICMLA.2016.0051"},{"key":"28_CR19","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: 4th International Conference on Learning Representations (ICLR), Proceedings. Proceedings of the International Conference on Learning Representations, San Juan, Puerto Rico, vol. 4 (2016)"},{"key":"28_CR20","first-page":"19523","volume":"35","author":"B Sorscher","year":"2022","unstructured":"Sorscher, B., Geirhos, R., Shekhar, S., Ganguli, S., Morcos, A.: Beyond neural scaling laws: beating power law scaling via data pruning. Adv. Neural. Inf. Process. Syst. 35, 19523\u201319536 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR21","unstructured":"Stooke, A., et al.: Open-ended learning leads to generally capable agents. arXiv preprint arXiv:2107.12808 (2021)"},{"key":"28_CR22","first-page":"23237","volume":"36","author":"S Sujit","year":"2023","unstructured":"Sujit, S., Nath, S., Braga, P., Ebrahimi Kahou, S.: Prioritizing samples in reinforcement learning with reducible loss. Adv. Neural. Inf. Process. Syst. 36, 23237\u201323258 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: International Conference on Intelligent Robots and Systems (IROS), Proceedings, Vilamoura, Portugal, pp. 5026\u20135033 (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Xiang, H., Cheng, J., Zhang, Q., Liu, J.: Synthesized prioritized data pruning based deep deterministic policy gradient algorithm improvement. In: 15th International Conference on Information and Automation (ICIA), Proceedings, Fujian, China, pp. 121\u2013126 (2018)","DOI":"10.1109\/ICInfA.2018.8812510"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04558-4_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:17:17Z","timestamp":1757589437000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04558-4_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"ISBN":["9783032045577","9783032045584"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04558-4_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"12 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}