{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:24:53Z","timestamp":1753889093769,"version":"3.37.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030054526"},{"type":"electronic","value":"9783030054533"}],"license":[{"start":{"date-parts":[[2018,12,30]],"date-time":"2018-12-30T00:00:00Z","timestamp":1546128000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-05453-3_8","type":"book-chapter","created":{"date-parts":[[2018,12,30]],"date-time":"2018-12-30T02:02:29Z","timestamp":1546135349000},"page":"161-181","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Safe Deep Reinforcement Learning Hybrid Electric Vehicle Energy Management"],"prefix":"10.1007","author":[{"given":"Roman","family":"Liessner","sequence":"first","affiliation":[]},{"given":"Ansgar Malte","family":"Dietermann","sequence":"additional","affiliation":[]},{"given":"Bernard","family":"B\u00e4ker","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,30]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35913-2","volume-title":"Vehicle Propulsion Systems: Introduction to Modeling and Optimization","author":"L Guzzella","year":"2013","unstructured":"Guzzella, L., Sciarretta, A.: Vehicle Propulsion Systems: Introduction to Modeling and Optimization, 3rd edn. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-35913-2","edition":"3"},{"doi-asserted-by":"crossref","unstructured":"Banvait, H., Anwar, S., Chen, Y.: A rule-based energy management strategy for plugin hybrid electric vehicle (PHEV). In: American Control Conference (2009)","key":"8_CR2","DOI":"10.1109\/ACC.2009.5160242"},{"unstructured":"Lee, H.-D., Koo, E.-S., Sul, S.-K., Kim, J.-S.: Torque control strategy for a parallel-hybrid vehicle using fuzzy logic. In: IEEE Industry Applications Magazine (2000)","key":"8_CR3"},{"doi-asserted-by":"crossref","unstructured":"Sivertsson, M., Sundstr\u00f6m, C., Eriksson, L.: Adaptive control of a hybrid powertrain with map-based ECMS. In: IFAC World Congress (2011)","key":"8_CR4","DOI":"10.3182\/20110828-6-IT-1002.02091"},{"doi-asserted-by":"crossref","unstructured":"Foellinger, O.: Optimale Regelung und Steuerung. Oldenbourg (1994). ISBN: 3486231162","key":"8_CR5","DOI":"10.1515\/9783486787306"},{"key":"8_CR6","volume-title":"Reinforcement Learning: An Introduction","author":"R Sutton","year":"2018","unstructured":"Sutton, R.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, Cambridge (2018)","edition":"2"},{"issue":"1","key":"8_CR7","doi-asserted-by":"crossref","first-page":"235","DOI":"10.3182\/20020721-6-ES-1901.01507","volume":"35","author":"F Kirschbaum","year":"2002","unstructured":"Kirschbaum, F., Back, M., Hart, M.: Determination of the fuel-optimal trajectory for a vehicle along a known route. IFAC Proc. Vol. 35(1), 235\u2013239 (2002)","journal-title":"IFAC Proc. Vol."},{"unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-dynamic programming (1996). ISBN: 1886529108","key":"8_CR8"},{"unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. CoRR, abs\/1509.02971 (2015)","key":"8_CR9"},{"doi-asserted-by":"crossref","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., Topcu, U.: Safe Reinforcement Learning via Shielding, CoRR, abs\/1708.08611 (2017)","key":"8_CR10","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"8_CR11","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436\u2013444 (2015)","journal-title":"Nature"},{"issue":"7540","key":"8_CR12","doi-asserted-by":"crossref","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"},{"unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. In: NIPS Deep Learning Workshop (2013)","key":"8_CR13"},{"unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: Proceedings of the 31st International Conference on Machine Learning (ICML 2014). Hrsg. von Tony Jebara und Eric P. Xing. JMLR Workshop und Conference Proceedings, pp. 387\u2013395 (2014)","key":"8_CR14"},{"issue":"1","key":"8_CR15","doi-asserted-by":"crossref","first-page":"165","DOI":"10.4271\/2017-26-0256","volume":"6","author":"R Liessner","year":"2017","unstructured":"Liessner, R., Dietermann, A., B\u00e4ker, B., L\u00fcpkes, K.: Generation of replacement vehicle speed cycles based on extensive customer data by means of Markov models and threshold accepting. SAE Int. J. Altern. Powertrains 6(1), 165\u2013173 (2017)","journal-title":"SAE Int. J. Altern. Powertrains"},{"doi-asserted-by":"crossref","unstructured":"Liessner, R., Dietermann, A., B\u00e4ker, B., L\u00fcpkes, K.: Derivation of real-world driving cycles corresponding to traffic situation and driving style on the basis of Markov models and cluster analyses. In: 6th Conference on Hybrid and Electric Vehicles, (HEVC 2016) (2016)","key":"8_CR16","DOI":"10.1049\/cp.2016.0961"},{"key":"8_CR17","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-6781-5","volume-title":"Hybrid Electric Vehicles: Energy Management Strategies","author":"S Onori","year":"2016","unstructured":"Onori, S., Serrao, L., Rizzoni, G.: Hybrid Electric Vehicles: Energy Management Strategies. Springer, London (2016)"},{"unstructured":"Helbing, M., B\u00e4ker, B., Schiffer, S.: Total vehicle concept design using computational intelligence. In: 6th Conference on Future Automotive Technology, F\u00fcrstenfeldbruck (2017)","key":"8_CR18"},{"unstructured":"Pillas, J.: Modellbasierte Optimierung dynamischer Fahrman\u00f6ver mittels Pr\u00fcfst\u00e4nden, Dissertation, Technischen Universit\u00e4t Darmstadt (2017)","key":"8_CR19"},{"doi-asserted-by":"crossref","unstructured":"Engelhardt, T.: Derating-Strategien f\u00fcr elektrisch angetriebene Sportwagen, Wissenschaftliche Reihe Fahrzeugtchnik Universit\u00e4t Stuttgart (2017)","key":"8_CR20","DOI":"10.1007\/978-3-658-18207-6"},{"unstructured":"Wei, L.: Introduction to Hybrid Vehicle System Modeling and Control. Wiley, Hoboken (2013). ISBN 978-1-118-30840-0","key":"8_CR21"},{"unstructured":"Duan, Y.: Benchmarking deep reinforcement learning for continuous control. In: Proceedings of the 33rd International Conference on Machine Learning (ICML) (2016)","key":"8_CR22"},{"unstructured":"Plappert, M., et al.: Parameter Space Noise for Exploration, CoRR, abs\/1706.01905 (2017)","key":"8_CR23"},{"unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization, CoRR, abs\/1412.6980 (2014)","key":"8_CR24"},{"unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier networks. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. JMLR W and CP Volume, vol. 15, pp. 315\u2013323 (2011)","key":"8_CR25"},{"issue":"5","key":"8_CR26","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1103\/PhysRev.36.823","volume":"36","author":"G Uhlenbeck","year":"1930","unstructured":"Uhlenbeck, G., Ornstein, L.: On the theory of the brownian motion. Phys. Rev. 36(5), 823 (1930)","journal-title":"Phys. Rev."},{"doi-asserted-by":"crossref","unstructured":"Liessner, R., Dietermann, A., Schroer C., B\u00e4ker, B.: Deep reinforcement learning for advanced energy management of hybrid electric vehicles. In: Proceedings of the 10th International Conference on Agents and Artificial Intelligence - (Volume 2) (2018)","key":"8_CR27","DOI":"10.5220\/0006573000610072"},{"unstructured":"Wu, Y., Mansimov, E., Liao, S., Grosse, R., Ba, J.: Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation, CoRR, abs\/1708.05144 (2017)","key":"8_CR28"},{"unstructured":"Mnih, V., et al.: Asynchronous Methods for Deep Reinforcement Learning, CoRR, abs\/1602.01783 (2016)","key":"8_CR29"},{"unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal Policy Optimization Algorithms, CoRR, abs\/1707.06347 (2017)","key":"8_CR30"}],"container-title":["Lecture Notes in Computer Science","Agents and Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05453-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,9]],"date-time":"2022-09-09T08:56:04Z","timestamp":1662713764000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05453-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,30]]},"ISBN":["9783030054526","9783030054533"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05453-3_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018,12,30]]},"assertion":[{"value":"ICAART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Agents and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Funchal","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 January 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 January 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icaart2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icaart.org\/?y=2018","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"}},{"value":"Primoris","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"161","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"45","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"42","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - 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"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"26 Posters","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}