{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T05:24:27Z","timestamp":1761110667163,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031218668"},{"type":"electronic","value":"9783031218675"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-21867-5_16","type":"book-chapter","created":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T11:04:07Z","timestamp":1670929447000},"page":"241-255","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Semi-model-Based Reinforcement Learning in\u00a0Organic Computing Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9307-855X","authenticated-orcid":false,"given":"Wenzel Pilar","family":"von Pilchau","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1808-9758","authenticated-orcid":false,"given":"Anthony","family":"Stein","sequence":"additional","affiliation":[]},{"given":"J\u00f6rg","family":"H\u00e4hner","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,12,14]]},"reference":[{"key":"16_CR1","unstructured":"Deisenroth, M., Rasmussen, C.E.: PILCO: a model-based and data-efficient approach to policy search. In: Proceedings of the 28th International Conference on machine learning (ICML-11), pp. 465\u2013472. Citeseer (2011)"},{"key":"16_CR2","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT press (2016)"},{"key":"16_CR3","doi-asserted-by":"publisher","unstructured":"van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30, no. 1 (2016). https:\/\/doi.org\/10.1609\/aaai.v30i1.10295, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/10295","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"16_CR4","doi-asserted-by":"publisher","unstructured":"Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning (2017). https:\/\/doi.org\/10.48550\/ARXIV.1710.02298","DOI":"10.48550\/ARXIV.1710.02298"},{"key":"16_CR5","unstructured":"Jacob, E.K.: Classification and categorization: a difference that makes a difference (2004). publisher: Graduate School of Library and Information Science. University of Illinois"},{"key":"16_CR6","unstructured":"Kaiser, L., et al.: Model-based reinforcement learning for atari. arXiv preprint arXiv:1903.00374 (2019)"},{"key":"16_CR7","unstructured":"LaValle, S.M., et al.: Rapidly-exploring random trees: a new tool for path planning. publisher: Ames. IA, USA (1998)"},{"key":"16_CR8","unstructured":"Levine, S., Abbeel, P.: Learning neural network policies with guided policy search under unknown dynamics. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"16_CR9","doi-asserted-by":"publisher","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning (2015). https:\/\/doi.org\/10.48550\/ARXIV.1509.02971","DOI":"10.48550\/ARXIV.1509.02971"},{"key":"16_CR10","unstructured":"Lin, L.J.: Reinforcement learning for robots using neural networks. Carnegie-Mellon Univ Pittsburgh Pa School of Computer Science, Technical report (1993)"},{"key":"16_CR11","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)"},{"key":"16_CR12","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. CoRR abs\/1312.5602 (2013). http:\/\/arxiv.org\/abs\/1312.5602"},{"issue":"7540","key":"16_CR13","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(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"16_CR14","doi-asserted-by":"publisher","unstructured":"Moerland, T.M., Broekens, J., Plaat, A., Jonker, C.M.: Model-based reinforcement learning: a survey (2020). https:\/\/doi.org\/10.48550\/ARXIV.2006.16712","DOI":"10.48550\/ARXIV.2006.16712"},{"issue":"1","key":"16_CR15","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/BF00993104","volume":"13","author":"AW Moore","year":"1993","unstructured":"Moore, A.W., Atkeson, C.G.: Prioritized sweeping: reinforcement learning with less data and less time. Mach. Learn. 13(1), 103\u2013130 (1993). https:\/\/doi.org\/10.1007\/BF00993104","journal-title":"Mach. Learn."},{"key":"16_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-0348-0130-0","volume-title":"Organic Computing-a Paradigm Shift for Complex Systems","author":"C M\u00fcller-Schloer","year":"2011","unstructured":"M\u00fcller-Schloer, C., Schmeck, H., Ungerer, T.: Organic Computing-a Paradigm Shift for Complex Systems. Springer, Cham (2011). https:\/\/doi.org\/10.1007\/978-3-0348-0130-0"},{"key":"16_CR17","doi-asserted-by":"publisher","unstructured":"M \u00fcller-Schloer, C., Tomforde, S.: Organic computing - technical systems for survival in the real world. Birkh \u00e4user (2017). https:\/\/doi.org\/10.1007\/978-3-319-68477-2","DOI":"10.1007\/978-3-319-68477-2"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Peng, B., Li, X., Gao, J., Liu, J., Wong, K.F., Su, S.Y.: Deep dyna-Q: integrating planning for task-completion dialogue policy learning. arXiv preprint arXiv:1801.06176 (2018)","DOI":"10.18653\/v1\/P18-1203"},{"key":"16_CR19","doi-asserted-by":"publisher","unstructured":"Pilar von Pilchau, W.: Averaging rewards as a first approach towards interpolated experience replay. In: Draude, C., Lange, M., Sick, B. (eds.) INFORMATIK 2019: 50 Jahre Gesellschaft f\u00fcr Informatik - Informatik f\u00fcr Gesellschaft (Workshop-Beitr\u00e4ge), pp. 493\u2013506. Gesellschaft f\u00fcr Informatik e.V., Bonn (2019). https:\/\/doi.org\/10.18420\/inf2019_ws53","DOI":"10.18420\/inf2019_ws53"},{"key":"16_CR20","doi-asserted-by":"publisher","unstructured":"Pilar von Pilchau, W., Stein, A., H\u00e4hner, J.: Bootstrapping a DQN replay memory with synthetic experiences. In: Merelo, J.J., Garibaldi, J., Wagner, C., B\u00e4ck, T., Madani, K., Warwick, K. (eds.) Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020), 2\u20134 November 2020 (2020). https:\/\/doi.org\/10.5220\/0010107904040411","DOI":"10.5220\/0010107904040411"},{"key":"16_CR21","doi-asserted-by":"publisher","unstructured":"Pilar von Pilchau, W., Stein, A., H\u00e4hner, J.: Synthetic experiences for accelerating DQN performance in discrete non-deterministic environments. Algorithms 14(8), 226 (2021). https:\/\/doi.org\/10.3390\/a14080226","DOI":"10.3390\/a14080226"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Pilar von Pilchau, W., Stein, A., H\u00e4hner, J.: Interpolated experience replay for continuous environments. In: Proceedings of the 14th International Joint Conference on Computational Intelligence (IJCCI 2020), 24\u201346 October 2022, p. to appear (2022)","DOI":"10.5220\/0011326900003332"},{"key":"16_CR23","series-title":"Autonomic Systems","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/978-3-0348-0130-0_28","volume-title":"Organic Computing \u2014 A Paradigm Shift for Complex Systems","author":"H Prothmann","year":"2011","unstructured":"Prothmann, H., et al.: Organic traffic control. In: M\u00fcller-Schloer, C., Schmeck, H., Ungerer, T. (eds.) Organic Computing \u2014 A Paradigm Shift for Complex Systems. Autonomic Systems, vol. 1, pp. 431\u2013446. Springer, Cham (2011). https:\/\/doi.org\/10.1007\/978-3-0348-0130-0_28"},{"key":"16_CR24","unstructured":"Sander, R.M.: Interpolated experience replay for improved sample efficiency of model-free deep reinforcement learning algorithms. Ph.D. thesis, Massachusetts Institute of Technology (2021)"},{"key":"16_CR25","doi-asserted-by":"publisher","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017). https:\/\/doi.org\/10.48550\/ARXIV.1707.06347","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"16_CR26","doi-asserted-by":"publisher","unstructured":"Schwarz, H., K\u00f6ckler, N.: Interpolation und approximation. In: Numerische Mathematik, pp. 91\u2013182. Vieweg+Teubner Verlag (2011). https:\/\/doi.org\/10.1007\/978-3-8348-8166-3_4","DOI":"10.1007\/978-3-8348-8166-3_4"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362(6419), 1140\u20131144 (2018)","DOI":"10.1126\/science.aar6404"},{"issue":"7676","key":"16_CR28","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of Go without human knowledge. Nature 550(7676), 354\u2013359 (2017). https:\/\/doi.org\/10.1038\/nature24270","journal-title":"Nature"},{"key":"16_CR29","doi-asserted-by":"publisher","unstructured":"Stein, A., Tomforde, S., Diaconescu, A., H\u00e4hner, J., M\u00fcller-Schloer, C.: A concept for proactive knowledge construction in self-learning autonomous systems. In: 2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W), pp. 204\u2013213 (2018). https:\/\/doi.org\/10.1109\/FAS-W.2018.00048","DOI":"10.1109\/FAS-W.2018.00048"},{"key":"16_CR30","doi-asserted-by":"publisher","unstructured":"Sutton, R.S.: Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In: Porter, B., Mooney, R. (eds.) Machine Learning Proceedings 1990, pp. 216\u2013224. Morgan Kaufmann, San Francisco (CA) (1990). https:\/\/doi.org\/10.1016\/B978-1-55860-141-3.50030-4","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"issue":"4","key":"16_CR31","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1145\/122344.122377","volume":"2","author":"RS Sutton","year":"1991","unstructured":"Sutton, R.S.: Dyna, an integrated architecture for learning, planning, and reacting. ACM Sigart Bull. 2(4), 160\u2013163 (1991)","journal-title":"ACM Sigart Bull."},{"key":"16_CR32","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press (2018)"},{"key":"16_CR33","unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. Adv. Neural Inf. Process. Syst. 12 (1999)"},{"key":"16_CR34","unstructured":"Tomforde, S., Sick, B., M\u00fcller-Schloer, C.: organic computing in the spotlight. CoRR abs\/1701.08125 (2017)"},{"key":"16_CR35","unstructured":"Van Hasselt, H.P., Hessel, M., Aslanides, J.: When to use parametric models in reinforcement learning? Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"16_CR36","unstructured":"Vanseijen, H., Sutton, R.: A deeper look at planning as learning from replay. In: International Conference on Machine Learning, pp. 2314\u20132322. PMLR (2015)"},{"key":"16_CR37","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1995\u20132003. PMLR (2016)"},{"issue":"3","key":"16_CR38","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992). https:\/\/doi.org\/10.1007\/BF00992698","journal-title":"Mach. Learn."}],"container-title":["Lecture Notes in Computer Science","Architecture of Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21867-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T11:07:04Z","timestamp":1670929624000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21867-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031218668","9783031218675"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21867-5_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"14 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ARCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Architecture of Computing Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heilbronn","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"arcs2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/arcs-conference.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"51% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,87","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}