{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T21:11:32Z","timestamp":1743109892000,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031708923"},{"type":"electronic","value":"9783031708930"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70893-0_22","type":"book-chapter","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T11:02:54Z","timestamp":1724929374000},"page":"292-299","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated Design in\u00a0Hybrid Action Spaces by\u00a0Reinforcement Learning and\u00a0Differential Evolution"],"prefix":"10.1007","author":[{"given":"Quirin","family":"G\u00f6ttl","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haris","family":"Asif","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Mattick","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Marzilger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Axel","family":"Plinge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,30]]},"reference":[{"key":"22_CR1","doi-asserted-by":"publisher","first-page":"073050","DOI":"10.1088\/1367-2630\/ab2e19","volume":"21","author":"P Azunre","year":"2019","unstructured":"Azunre, P., Jean, J., Rotschild, C., Bulovic, V., Johnson, S.G., Baldo, M.A.: Guaranteed global optimization of thin-film optical systems. New J. Phys. 21, 073050 (2019). https:\/\/doi.org\/10.1088\/1367-2630\/ab2e19","journal-title":"New J. Phys."},{"key":"22_CR2","unstructured":"Danihelka, I., Guez, A., Schrittwieser, J., Silver, D.: Policy improvement by planning with Gumbel. In: International Conference on Learning Representations (2022)"},{"key":"22_CR3","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TEVC.2010.2059031","volume":"15","author":"S Das","year":"2011","unstructured":"Das, S., Suganthan, P.N.: Differential evolution: a survey of the state-of-the-art. IEEE Trans. Evol. Comput. 15, 4\u201331 (2011). https:\/\/doi.org\/10.1109\/TEVC.2010.2059031","journal-title":"IEEE Trans. Evol. Comput."},{"key":"22_CR4","unstructured":"Dulac-Arnold, G., Mankowitz, D., Hester, T.: Challenges of real-world reinforcement learning. In: International Conference on Machine Learning (2019)"},{"key":"22_CR5","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1038\/s41586-022-05172-4","volume":"610","author":"A Fawzi","year":"2022","unstructured":"Fawzi, A., Balog, M., Huang, A., et al.: Discovering faster matrix multiplication algorithms with reinforcement learning. Nature 610, 47\u201353 (2022). https:\/\/doi.org\/10.1038\/s41586-022-05172-4","journal-title":"Nature"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Fu, H., Tang, H., Hao, J., Lei, Z., Chen, Y., Fan, C.: Deep multi-agent reinforcement learning with discrete-continuous hybrid action spaces. In: International Joint Conference on Artificial Intelligence (2019)","DOI":"10.24963\/ijcai.2019\/323"},{"key":"22_CR7","doi-asserted-by":"publisher","first-page":"120021","DOI":"10.1016\/j.apenergy.2022.120021","volume":"326","author":"Y Gao","year":"2022","unstructured":"Gao, Y., Matsunami, Y., Miyata, S., Akashi, Y.: Multi-agent reinforcement learning dealing with hybrid action spaces: a case study for off-grid oriented renewable building energy system. Appl. Energy 326, 120021 (2022). https:\/\/doi.org\/10.1016\/j.apenergy.2022.120021","journal-title":"Appl. Energy"},{"key":"22_CR8","doi-asserted-by":"publisher","first-page":"101012","DOI":"10.1016\/j.coche.2024.101012","volume":"44","author":"Q Gao","year":"2024","unstructured":"Gao, Q., Schweidtmann, A.M.: Deep reinforcement learning for process design: review and perspective. Curr. Opin. Chem. Eng. 44, 101012 (2024). https:\/\/doi.org\/10.1016\/j.coche.2024.101012","journal-title":"Curr. Opin. Chem. Eng."},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"G\u00f6ttl, Q., Pirnay, J., Burger, J., Grimm, D.G.: Deep reinforcement learning uncovers processes for separating azeotropic mixtures without prior knowledge. arXiv:2310.06415 (2023)","DOI":"10.2139\/ssrn.4776784"},{"issue":"12","key":"22_CR10","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1002\/cite.202100086","volume":"93","author":"Q G\u00f6ttl","year":"2021","unstructured":"G\u00f6ttl, Q., T\u00f6nges, Y., Grimm, D.G., Burger, J.: Automated flowsheet synthesis using hierarchical reinforcement learning: proof of concept. Chem. Ing. Tec. 93(12), 2010\u20132018 (2021). https:\/\/doi.org\/10.1002\/cite.202100086","journal-title":"Chem. Ing. Tec."},{"issue":"12","key":"22_CR11","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1016\/j.compchemeng.2019.04.028","volume":"126","author":"IE Grossmann","year":"2019","unstructured":"Grossmann, I.E., Harjunkoski, I.: Process systems engineering: academic and industrial perspectives. Comput. Chem. Eng. 126(12), 474\u2013484 (2019). https:\/\/doi.org\/10.1016\/j.compchemeng.2019.04.028","journal-title":"Comput. Chem. Eng."},{"key":"22_CR12","unstructured":"Hausknecht, M.J., Stone, P.: Deep reinforcement learning in parameterized action space. In: International Conference on Learning Representations (2016)"},{"issue":"12","key":"22_CR13","doi-asserted-by":"publisher","first-page":"3802","DOI":"10.3390\/molecules27123802","volume":"27","author":"Z Hu","year":"2022","unstructured":"Hu, Z., Li, P., Liu, Y.: Enhancing the performance of evolutionary algorithm by differential evolution for optimizing distillation sequence. Molecules 27(12), 3802 (2022). https:\/\/doi.org\/10.3390\/molecules27123802","journal-title":"Molecules"},{"key":"22_CR14","unstructured":"Hubert, T., Schrittwieser, J., Antonoglou, I., Barekatain, M., Schmitt, S., Silver, D.: Learning and planning in complex action spaces. In: International Conference on Machine Learning (2021)"},{"key":"22_CR15","doi-asserted-by":"publisher","first-page":"12780","DOI":"10.1038\/s41598-020-69754-w","volume":"10","author":"A Jiang","year":"2020","unstructured":"Jiang, A., Osamu, Y., Chen, L.: Multilayer optical thin film design with deep Q learning. Sci. Rep. 10, 12780 (2020). https:\/\/doi.org\/10.1038\/s41598-020-69754-w","journal-title":"Sci. Rep."},{"key":"22_CR16","doi-asserted-by":"publisher","first-page":"108885","DOI":"10.1016\/j.cep.2022.108885","volume":"180","author":"AA Khan","year":"2022","unstructured":"Khan, A.A., Lapkin, A.A.: Designing the process designer: hierarchical reinforcement learning for optimisation-based process design. Chem. Eng. Process. Process Intensification 180, 108885 (2022). https:\/\/doi.org\/10.1016\/j.cep.2022.108885","journal-title":"Chem. Eng. Process. Process Intensification"},{"key":"22_CR17","doi-asserted-by":"publisher","unstructured":"Li, D.G., Watson, A.C.: Optical thin film optimization design using genetic algorithms. In: IEEE International Conference on Intelligent Processing Systems (1997). https:\/\/doi.org\/10.1109\/ICIPS.1997.672752","DOI":"10.1109\/ICIPS.1997.672752"},{"key":"22_CR18","unstructured":"Mahmood, A.R., Korenkevych, D., Vasan, G., Ma, W., Bergstra, J.: Benchmarking reinforcement learning algorithms on real-world robots. In: Conference on Robot Learning (2018)"},{"key":"22_CR19","doi-asserted-by":"publisher","unstructured":"Martin, M., Adams II, T.A.: Challenges and future directions for process and product synthesis and design. Comput. Chem. Eng. 128, 421-436 (2019). https:\/\/doi.org\/10.1016\/j.compchemeng.2019.06.022","DOI":"10.1016\/j.compchemeng.2019.06.022"},{"key":"22_CR20","unstructured":"Neunert, M., et al.: Continuous-discrete reinforcement learning for hybrid control in robotics. In: Conference on Robot Learning (2019)"},{"key":"22_CR21","doi-asserted-by":"publisher","unstructured":"Pan, F., Zhang, T., Luo, L., He, J., Liu, S.: Learn continuously, act discretely: hybrid action-space reinforcement learning for optimal execution. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (2022). https:\/\/doi.org\/10.48550\/ARXIV.2207.11152","DOI":"10.48550\/ARXIV.2207.11152"},{"key":"22_CR22","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., Schrittwieser, J., Simonyan, K., et al.: Mastering the game of go without human knowledge. Nature 550, 354\u2013359 (2017). https:\/\/doi.org\/10.1038\/nature24270","journal-title":"Nature"},{"issue":"1","key":"22_CR23","doi-asserted-by":"publisher","first-page":"e17938","DOI":"10.1002\/aic.17938","volume":"69","author":"L Stops","year":"2023","unstructured":"Stops, L., Leenhouts, R., Gao, Q., Schweidtmann, A.M.: Flowsheet generation through hierarchical reinforcement learning and graph neural networks. AIChE J. 69(1), e17938 (2023). https:\/\/doi.org\/10.1002\/aic.17938","journal-title":"AIChE J."},{"key":"22_CR24","doi-asserted-by":"publisher","first-page":"3668","DOI":"10.1109\/TCYB.2019.2950779","volume":"50","author":"S Sun","year":"2019","unstructured":"Sun, S., Cao, Z., Zhu, H., Zhao, J.: A survey of optimization methods from a machine learning perspective. IEEE Trans. Cybern. 50, 3668\u20133681 (2019). https:\/\/doi.org\/10.1109\/TCYB.2019.2950779","journal-title":"IEEE Trans. Cybern."},{"key":"22_CR25","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press, Cambridge (2018)","edition":"2"},{"key":"22_CR26","unstructured":"Tolstikhin, I.O., et al.: MLP-mixer: an all-MLP architecture for vision. Neural Inf. Process. Syst. (2021)"},{"key":"22_CR27","doi-asserted-by":"publisher","unstructured":"Wang, H., Zheng, Z., Ji, C., Guo, L.J.: Automated multi-layer optical design via deep reinforcement learning. Mach. Learn. Sci. Technol. 2, 025013 (2021). https:\/\/doi.org\/10.1088\/2632-2153\/abc327","DOI":"10.1088\/2632-2153\/abc327"},{"key":"22_CR28","doi-asserted-by":"publisher","first-page":"305104","DOI":"10.1088\/1361-6463\/abfddb","volume":"54","author":"H Wankerl","year":"2021","unstructured":"Wankerl, H., Stern, M.L., Mahdavi, A., Eichler, C., Lang, E.W.: Parameterized reinforcement learning for optical system optimization. J. Phys. D Appl. Phys. 54, 305104 (2021). https:\/\/doi.org\/10.1088\/1361-6463\/abfddb","journal-title":"J. Phys. D Appl. Phys."},{"issue":"4","key":"22_CR29","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1016\/j.compchemeng.2003.09.029","volume":"28","author":"A Westerberg","year":"2004","unstructured":"Westerberg, A.: A retrospective on design and process synthesis. Comput. Chem. Eng. 28(4), 447\u2013458 (2004). https:\/\/doi.org\/10.1016\/j.compchemeng.2003.09.029","journal-title":"Comput. Chem. Eng."},{"key":"22_CR30","doi-asserted-by":"publisher","first-page":"252","DOI":"10.3390\/machines12040252","volume":"12","author":"R Xu","year":"2024","unstructured":"Xu, R., Xu, J., Liu, X., Lin, Y.: Safe hybrid-action reinforcement learning-based decision and control for discretionary lane change. Machines 12, 252 (2024). https:\/\/doi.org\/10.3390\/machines12040252","journal-title":"Machines"}],"container-title":["Lecture Notes in Computer Science","KI 2024: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70893-0_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T11:07:31Z","timestamp":1724929651000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70893-0_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031708923","9783031708930"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70893-0_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"30 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"German Conference on Artificial Intelligence (K\u00fcnstliche Intelligenz)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"W\u00fcrzburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"25 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"47","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ki2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.informatik.uni-wuerzburg.de\/ki24\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}