{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T01:21:48Z","timestamp":1742952108356,"version":"3.40.3"},"publisher-location":"Cham","reference-count":8,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030304928"},{"type":"electronic","value":"9783030304935"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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\/978-3-030-30493-5_40","type":"book-chapter","created":{"date-parts":[[2019,9,10]],"date-time":"2019-09-10T20:03:41Z","timestamp":1568145821000},"page":"403-407","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning Informed by Optimal Control"],"prefix":"10.1007","author":[{"given":"Magnus","family":"\u00d6nnheim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pontus","family":"Andersson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emil","family":"Gustavsson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mats","family":"Jirstrand","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,9]]},"reference":[{"key":"40_CR1","volume-title":"Control Theory","author":"T Glad","year":"2000","unstructured":"Glad, T., Ljung, L.: Control Theory. Taylor & Francis, London (2000)"},{"key":"40_CR2","unstructured":"Hill, A., et al.: Stable baselines (2019). https:\/\/github.com\/hill-a\/stable-baselines"},{"issue":"3","key":"40_CR3","doi-asserted-by":"publisher","first-page":"2471","DOI":"10.1109\/LRA.2018.2800106","volume":"3","author":"I Koryakovskiy","year":"2018","unstructured":"Koryakovskiy, I., Kudruss, M., Vallery, H., Babu\u0161ka, R., Caarls, W.: Model-plant mismatch compensation using reinforcement learning. IEEE Robot. Autom. Lett. 3(3), 2471\u20132477 (2018)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"40_CR4","first-page":"278","volume":"99","author":"AY Ng","year":"1999","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations. ICML 99, 278\u2013287 (1999)","journal-title":"ICML"},{"key":"40_CR5","unstructured":"Rastogi, D., Koryakovskiy, I., Kober, J.: Sample-efficient reinforcement learning via difference models. In: Machine Learning in Planning and Control of Robot Motion Workshop at ICRA (2018)"},{"key":"40_CR6","unstructured":"Recht, B.: A tour of reinforcement learning. AAnnu. Rev. Control. Robot. Auton. Syst. (2018)"},{"key":"40_CR7","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 (2015)"},{"key":"40_CR8","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Workshop and Special Sessions"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-30493-5_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T16:51:14Z","timestamp":1710348674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-30493-5_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030304928","9783030304935"],"references-count":8,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-30493-5_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}