{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:17:43Z","timestamp":1783765063256,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","funder":[{"DOI":"10.13039\/100014440","name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","doi-asserted-by":"publisher","award":["PID2021-127647NB-C21"],"award-info":[{"award-number":["PID2021-127647NB-C21"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,14]]},"DOI":"10.1145\/3712256.3726364","type":"proceedings-article","created":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T12:28:18Z","timestamp":1751977698000},"page":"416-424","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Dataset Reduction for Offline Reinforcement Learning using Genetic Algorithms with Image-Based Heuristics"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9314-8062","authenticated-orcid":false,"given":"Enrique","family":"Mateos-Melero","sequence":"first","affiliation":[{"name":"Universidad Carlos III de Madrid, Legan\u00e9s, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8100-4974","authenticated-orcid":false,"given":"Miguel","family":"Iglesias Alc\u00e1zar","sequence":"additional","affiliation":[{"name":"Universidad Carlos III de Madrid, Legan\u00e9s, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3856-2629","authenticated-orcid":false,"given":"Raquel","family":"Fuentetaja","sequence":"additional","affiliation":[{"name":"Universidad Carlos III de Madrid, Legan\u00e9s, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3801-6801","authenticated-orcid":false,"given":"Fernando","family":"Fern\u00e1ndez","sequence":"additional","affiliation":[{"name":"Universidad Carlos III de Madrid, Legan\u00e9s, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Data Valuation for Offline Reinforcement Learning. arXiv 2205.09550","author":"Abolfazli Amir","year":"2022","unstructured":"Amir Abolfazli, Gregory Palmer, and Daniel Kudenko. 2022. Data Valuation for Offline Reinforcement Learning. arXiv 2205.09550 (2022), 9 pages."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"e_1_3_2_2_3_1","volume-title":"Machine Learning for Data Science Handbook: Data Mining and Knowledge Discovery Handbook","author":"Bank Dor","unstructured":"Dor Bank, Noam Koenigstein, and Raja Giryes. 2023. Autoencoders. In Machine Learning for Data Science Handbook: Data Mining and Knowledge Discovery Handbook. Springer International Publishing, 353\u2013374."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning. PMLR, 2242\u20132251","author":"Ghorbani Amirata","year":"2019","unstructured":"Amirata Ghorbani and Jame Zou. 2019. Data shapley: Equitable valuation of data for machine learning. In Proceedings of the 36th International Conference on Machine Learning. PMLR, 2242\u20132251."},{"key":"e_1_3_2_2_5_1","volume-title":"Generative Adversarial Nets. In Advances in Neural Information Processing Systems. Proceedings of the twenty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS","volume":"27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems. Proceedings of the twenty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2014), Vol. 27. Curran Associates, 2672\u20132680."},{"key":"e_1_3_2_2_6_1","volume-title":"Generative Adversarial Imitation Learning. In Advances in Neural Information Processing Systems. Proceedings of the thirtieth Annual Conference on Neural Information Processing Systems (NeurIPS","volume":"29","author":"Ho Jonathan","year":"2016","unstructured":"Jonathan Ho and Stefano Ermon. 2016. Generative Adversarial Imitation Learning. In Advances in Neural Information Processing Systems. Proceedings of the thirtieth Annual Conference on Neural Information Processing Systems (NeurIPS 2016), Vol. 29. Curran Associates, 4565\u20134573."},{"key":"e_1_3_2_2_7_1","volume-title":"Adaptation in Natural and Artificial Systems","author":"Holland John H.","unstructured":"John H. Holland. 1975. Adaptation in Natural and Artificial Systems. MIT Press."},{"key":"e_1_3_2_2_8_1","volume-title":"Event Tables for Efficient Experience Replay. Transactions on Machine Learning Research","author":"Kompella Varun Raj","year":"2023","unstructured":"Varun Raj Kompella, Thomas Walsh, Samuel Barrett, Peter R. Wurman, and Peter Stone. 2023. Event Tables for Efficient Experience Replay. Transactions on Machine Learning Research (2023), 32 pages."},{"key":"e_1_3_2_2_9_1","volume-title":"On information and sufficiency. The Annals of Mathematical Statistics 22(1)","author":"Kullback Solomon","year":"1951","unstructured":"Solomon Kullback and Richard A Leibler. 1951. On information and sufficiency. The Annals of Mathematical Statistics 22(1) (1951), 79\u201386."},{"key":"e_1_3_2_2_10_1","volume-title":"Advances in Neural Information Processing Systems. Proceedings of the thirty-fourth Annual Conference on Neural Information Processing Systems (NeurIPS","author":"Kumar Aviral","year":"2020","unstructured":"Aviral Kumar, Aurick Zhou, George Tucker, and Sergey Levine. 2020. Conservative Q-Learning for Offline Reinforcement Learning. In Advances in Neural Information Processing Systems. Proceedings of the thirty-fourth Annual Conference on Neural Information Processing Systems (NeurIPS 2020), Vol. 33. Curran Associates, 1179\u20131191."},{"key":"e_1_3_2_2_11_1","volume-title":"Batch reinforcement learning","author":"Lange Sascha","unstructured":"Sascha Lange, Thomas Gabel, and Martin Riedmiller. 2012. Batch reinforcement learning. Springer. 45\u201373 pages."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_2_13_1","article-title":"Offline Reinforcement Learning","volume":"2005","author":"Levine Sergey","year":"2020","unstructured":"Sergey Levine, Aviral Kumar, G. Tucker, and Justin Fu. 2020. Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems. ArXiv 2005.01643 (2020), 43 pages.","journal-title":"Tutorial, Review, and Perspectives on Open Problems. ArXiv"},{"key":"e_1_3_2_2_14_1","volume-title":"Curriculum Offline Imitating Learning. In Advances in Neural Information Processing Systems. Proceedings of the thirty-fifth Annual Conference on Neural Information Processing Systems (NeurIPS","author":"Liu Minghuan","year":"2021","unstructured":"Minghuan Liu, Hanye Zhao, Zhengyu Yang, Jian Shen, Weinan Zhang, Li Zhao, and Tie-Yan Liu. 2021. Curriculum Offline Imitating Learning. In Advances in Neural Information Processing Systems. Proceedings of the thirty-fifth Annual Conference on Neural Information Processing Systems (NeurIPS 2021). Curran Associates, 1\u201312."},{"key":"e_1_3_2_2_15_1","volume-title":"Genetic algorithms + data structures = evolution programs (3nd, extended ed.)","author":"Michalewicz Z.","unstructured":"Z. Michalewicz. 1996. Genetic algorithms + data structures = evolution programs (3nd, extended ed.). Springer, New York, NY, USA."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/2691759"},{"key":"e_1_3_2_2_17_1","volume-title":"On lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin philosophical magazine and journal of science 2(11)","author":"Pearson Karl","year":"1901","unstructured":"Karl Pearson. 1901. LIII. On lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin philosophical magazine and journal of science 2(11) (1901), 559\u2013572."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/4235.850656"},{"key":"e_1_3_2_2_19_1","volume-title":"Understanding the Effects of Dataset Characteristics on Offline Reinforcement Learning. In Deep RL Workshop NeurIPS","author":"Schweighofer Kajetan","year":"2021","unstructured":"Kajetan Schweighofer, Markus Hofmarcher, Marius-Constantin Dinu, Philipp Renz, Angela Bitto-Nemling, Vihang Prakash Patil, and Sepp Hochreiter. 2021. Understanding the Effects of Dataset Characteristics on Offline Reinforcement Learning. In Deep RL Workshop NeurIPS 2021. 19 pages."},{"key":"e_1_3_2_2_20_1","volume-title":"2008 Eighth International Conference on Hybrid Intelligent Systems. 573\u2013578","author":"Leila","unstructured":"Leila S. Shafti and Eduardo P\u00e9rez. 2008. Data Reduction by Genetic Algorithms and Non-Algebraic Feature Construction: A Case Study. In 2008 Eighth International Conference on Hybrid Intelligent Systems. 573\u2013578."},{"key":"e_1_3_2_2_21_1","volume-title":"Barto","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction (second ed.). The MIT Press."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI50451.2021.9660006"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/1577069.1755839"},{"key":"e_1_3_2_2_24_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research 9, 86 (2008), 2579\u20132605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_25_1","volume-title":"Behavior Regularized Offline Reinforcement Learning. arXiv","author":"Wu Yifan","year":"1911","unstructured":"Yifan Wu, George Tucker, and Ofir Nachum. 2019. Behavior Regularized Offline Reinforcement Learning. arXiv 1911.11361 (2019), 25 pages."},{"key":"e_1_3_2_2_26_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Wu Yueh-Hua","year":"2019","unstructured":"Yueh-Hua Wu, Nontawat Charoenphakdee, Han Bao, Voot Tangkaratt, and Masashi Sugiyama. 2019. Imitation Learning from Imperfect Demonstration. In Proceedings of the 36th International Conference on Machine Learning, Vol. 97. PMLR, 6818\u20136827."},{"key":"e_1_3_2_2_27_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Xu Haoran","year":"2022","unstructured":"Haoran Xu, Xianyuan Zhan, Honglei Yin, and Huiling Qin. 2022. Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations. In Proceedings of the 39th International Conference on Machine Learning, Vol. 162. PMLR, 24725\u201324742."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525943"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26326"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"}],"event":{"name":"GECCO '25: Genetic and Evolutionary Computation Conference","location":"NH Malaga Hotel Malaga Spain","acronym":"GECCO '25","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"]},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712256.3726364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T20:43:22Z","timestamp":1759869802000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712256.3726364"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":31,"alternative-id":["10.1145\/3712256.3726364","10.1145\/3712256"],"URL":"https:\/\/doi.org\/10.1145\/3712256.3726364","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}