{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T23:07:17Z","timestamp":1779923237833,"version":"3.53.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032214799","type":"print"},{"value":"9783032214805","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-21480-5_11","type":"book-chapter","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T22:38:58Z","timestamp":1779921538000},"page":"159-173","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Genetic Algorithms for Efficient Demonstration Generation in Real-World Reinforcement Learning Environments"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3496-5964","authenticated-orcid":false,"given":"Tom","family":"Maus","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9666-7225","authenticated-orcid":false,"given":"Asma","family":"Atamna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1886-1696","authenticated-orcid":false,"given":"Tobias","family":"Glasmachers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Mathew, D., Brintha, N.C., Jappes, J.T.W.: artificial intelligence powered automation for industry 4.0. In: Nayyar, A., Naved, M., Rameshwar, R. (eds.) New Horizons for Industry 4.0 in Modern Business, pp. 1\u201328. Springer, Cham (2023)","DOI":"10.1007\/978-3-031-20443-2_1"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"del Real Torres, A., Andreiana, D.S., Ojeda Rold\u00e1n, \u00c1., Hern\u00e1ndez Bustos, A., Acevedo Galicia, L.E.: A review of deep reinforcement learning approaches for smart manufacturing in Industry 4.0 and 5.0 framework. Appl. Sci. 12, 12377 (2022)","DOI":"10.3390\/app122312377"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Cronrath, C., Aderiani, A.R., Lennartson, B.: Enhancing digital twins through reinforcement learning. In: 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE), pp. 293\u2013298. IEEE, Vancouver (2019)","DOI":"10.1109\/COASE.2019.8842888"},{"key":"11_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115036","volume":"269","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Hong, T.: Reinforcement learning for building controls: the opportunities and challenges. Appl. Energy 269, 115036 (2020)","journal-title":"Appl. Energy"},{"key":"11_CR5","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (2018)"},{"key":"11_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106886","volume":"139","author":"R Nian","year":"2020","unstructured":"Nian, R., Liu, J., Huang, B.: A review on reinforcement learning: introduction and applications in industrial process control. Comput. Chem. Eng. 139, 106886 (2020)","journal-title":"Comput. Chem. Eng."},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Yu, Y.: Towards sample efficient reinforcement learning. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (2018)","DOI":"10.24963\/ijcai.2018\/820"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Hester, T., et al.: Deep Q-learning from demonstrations. In: Proceedings of AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Torabi, F., Warnell, G., Stone, P.: Behavioral cloning from observation. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, pp. 4950\u20134957. International Joint Conferences on Artificial Intelligence Organization, Stockholm (2018)","DOI":"10.24963\/ijcai.2018\/687"},{"key":"11_CR10","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1038\/scientificamerican0792-66","volume":"267","author":"JH Holland","year":"1992","unstructured":"Holland, J.H.: Genetic algorithms. Sci. Am. 267, 66\u201373 (1992)","journal-title":"Sci. Am."},{"key":"11_CR11","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"11_CR12","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: proximal policy optimization algorithms (2017). http:\/\/arxiv.org\/abs\/1707.06347"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Pendyala, A., Dettmer, J., Glasmachers, T., Atamna, A.: ContainerGym: a real-world reinforcement learning benchmark for resource allocation (2023)","DOI":"10.1007\/978-3-031-53969-5_7"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Maus, T., Zengeler, N., Glasmachers, T.: SortingEnv: an extendable RL-environment for an industrial sorting process (2025). https:\/\/arxiv.org\/abs\/2503.10466","DOI":"10.1063\/5.0308534"},{"key":"11_CR15","doi-asserted-by":"publisher","first-page":"2834","DOI":"10.3390\/en15082834","volume":"15","author":"D Lee","year":"2022","unstructured":"Lee, D., Koo, S., Jang, I., Kim, J.: Comparison of deep reinforcement learning and PID controllers for automatic cold shutdown operation. Energies 15, 2834 (2022)","journal-title":"Energies"},{"key":"11_CR16","unstructured":"Louette, A., Lambrechts, G., Ernst, D., Pirard, E., Dislaire, G.: Reinforcement Learning to improve delta robot throws for sorting scrap metal (2024). http:\/\/arxiv.org\/abs\/2406.13453"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Farooq, A., Iqbal, K.: A survey of reinforcement learning for optimization in automation. In: 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE), pp. 2487\u20132494 (2024)","DOI":"10.1109\/CASE59546.2024.10711718"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Bain, M., Sammut, C.: A framework for behavioural cloning. In: Machine Intelligence, vol. 15, pp. 103\u2013129. Oxford University PressOxford (2000)","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"11_CR19","unstructured":"Ross, S., Gordon, G.J., Bagnell, J.A.: A reduction of imitation learning and structured prediction to no-regret online learning (2011). http:\/\/arxiv.org\/abs\/1011.0686"},{"key":"11_CR20","unstructured":"Vecerik, M., et al.: Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards (2018). http:\/\/arxiv.org\/abs\/1707.08817"},{"key":"11_CR21","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay (2016)"},{"key":"11_CR22","doi-asserted-by":"publisher","first-page":"7173","DOI":"10.1109\/TCYB.2024.3395626","volume":"54","author":"M Zare","year":"2024","unstructured":"Zare, M., Kebria, P.M., Khosravi, A., Nahavandi, S.: A survey of imitation learning: algorithms, recent developments, and challenges. IEEE Trans. Cybern. 54, 7173\u20137186 (2024)","journal-title":"IEEE Trans. Cybern."},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Zheng, B., Zhou, J., Ma, J., Chen, F.: Genetic imitation learning by reward extrapolation. In: 2024 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138 (2024)","DOI":"10.1109\/IJCNN60899.2024.10650998"},{"key":"11_CR24","doi-asserted-by":"publisher","DOI":"10.1049\/tje2.12393","volume":"2024","author":"Y Ruan","year":"2024","unstructured":"Ruan, Y., Cai, W., Wang, J.: Combining reinforcement learning algorithm and genetic algorithm to solve the traveling salesman problem. J. Eng. 2024, e12393 (2024)","journal-title":"J. Eng."},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Altmann, P., Davignon, C., Zorn, M., Ritz, F., Linnhoff-Popien, C., Gabor, T.: REACT: revealing evolutionary action consequence trajectories for interpretable reinforcement learning. In: Proceedings of the 16th International Joint Conference on Computational Intelligence, pp. 127\u2013138. SCITEPRESS - Science and Technology Publications, Porto (2024)","DOI":"10.5220\/0013005900003837"},{"key":"11_CR26","unstructured":"Towers, M., et al.: Gymnasium (2023). https:\/\/zenodo.org\/record\/8127026"},{"key":"11_CR27","unstructured":"Gleave, A., et al.: Limitation: clean imitation learning implementations (2022)"},{"key":"11_CR28","first-page":"1","volume":"22","author":"A Raffin","year":"2021","unstructured":"Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-Baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22, 1\u20138 (2021)","journal-title":"J. Mach. Learn. Res."}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-21480-5_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T22:39:02Z","timestamp":1779921542000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21480-5_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032214799","9783032214805"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21480-5_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Artificial Intelligence Symposium","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Castiglione della Pescaia","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2025.icas.events","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}