{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:59:21Z","timestamp":1740099561960,"version":"3.37.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030332730"},{"type":"electronic","value":"9783030332747"}],"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\/978-3-030-33274-7_11","type":"book-chapter","created":{"date-parts":[[2019,10,17]],"date-time":"2019-10-17T04:06:31Z","timestamp":1571285191000},"page":"160-174","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Toward Faster Reinforcement Learning for Robotics: Using Gaussian Processes"],"prefix":"10.1007","author":[{"given":"Ali","family":"Younes","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9747-3837","authenticated-orcid":false,"given":"Aleksandr I.","family":"Panov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,10,14]]},"reference":[{"key":"11_CR1","series-title":"Lecture Notes in Control and Information Sciences","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0043199","volume-title":"Robust Controller Design Procedure Using Normalized Coprime Factor Plant Descriptions","author":"DC McFarlane","year":"1990","unstructured":"McFarlane, D.C., Glover, K.: Robust Controller Design Procedure Using Normalized Coprime Factor Plant Descriptions. Lecture Notes in Control and Information Sciences, vol. 138. Springer, Heidelberg (1990). \n                      https:\/\/doi.org\/10.1007\/BFb0043199"},{"issue":"4","key":"11_CR2","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1109\/70.508444","volume":"12","author":"P Rocco","year":"1996","unstructured":"Rocco, P.: Stability of PID control for industrial robot arms. IEEE Trans. Robot. Autom. 12(4), 606\u2013614 (1996)","journal-title":"IEEE Trans. Robot. Autom."},{"key":"11_CR3","volume-title":"Adaptive Control","author":"KJ \u00c5str\u00f6m","year":"2013","unstructured":"\u00c5str\u00f6m, K.J., Wittenmark, B.: Adaptive Control. Courier Corporation, Mineola (2013)"},{"key":"11_CR4","unstructured":"Wen, J.T., Murphy, S.H.: PID control for robot manipulators. Rensselaer Polytechnic Institute (1990)"},{"issue":"1","key":"11_CR5","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1023\/A:1009694129740","volume":"12","author":"RA Teixeira","year":"2000","unstructured":"Teixeira, R.A., Braga, A.D.P., De Menezes, B.R.: Control of a robotic manipulator using artificial neural networks with on-line adaptation. Neural Process. Lett. 12(1), 19\u201331 (2000)","journal-title":"Neural Process. Lett."},{"issue":"1","key":"11_CR6","doi-asserted-by":"publisher","first-page":"5","DOI":"10.5772\/5766","volume":"3","author":"IA Nesnas","year":"2006","unstructured":"Nesnas, I.A., et al.: CLARAty: challenges and steps toward reusable robotic software. Int. J. Adv. Robot. Syst. 3(1), 5 (2006)","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"11_CR7","volume-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, vol. 135. MIT Press, Cambridge (1998)"},{"key":"11_CR8","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"11_CR9","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897, June 2015"},{"key":"11_CR10","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint \n                      arXiv:1707.06347\n                      \n                     (2017)"},{"key":"11_CR11","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint \n                      arXiv:1509.02971\n                      \n                     (2015)"},{"issue":"7540","key":"11_CR12","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 (2015)","journal-title":"Nature"},{"issue":"7553","key":"11_CR13","doi-asserted-by":"publisher","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(7553), 436 (2015)","journal-title":"Nature"},{"issue":"1-2","key":"11_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2300000021","volume":"2","author":"Marc Peter Deisenroth","year":"2011","unstructured":"Deisenroth, M.P., Neumann, G., Peters, J.: A survey on policy search for robotics. Found. Trends\u00ae Robot. 2(1\u20132), 1\u2013142 (2013)","journal-title":"Foundations and Trends in Robotics"},{"issue":"3","key":"11_CR15","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TRO.2004.838027","volume":"21","author":"J Carlson","year":"2005","unstructured":"Carlson, J., Murphy, R.R.: How UGVs physically fail in the field. IEEE Trans. Robot. 21(3), 423\u2013437 (2005)","journal-title":"IEEE Trans. Robot."},{"issue":"7553","key":"11_CR16","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1038\/nature14422","volume":"521","author":"A Cully","year":"2015","unstructured":"Cully, A., Clune, J., Tarapore, D., Mouret, J.B.: Robots that can adapt like animals. Nature 521(7553), 503 (2015)","journal-title":"Nature"},{"issue":"1","key":"11_CR17","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1002\/rob.21439","volume":"30","author":"K Nagatani","year":"2013","unstructured":"Nagatani, K., et al.: Emergency response to the nuclear accident at the Fukushima Daiichi Nuclear Power Plants using mobile rescue robots. J. Field Robot. 30(1), 44\u201363 (2013)","journal-title":"J. Field Robot."},{"key":"11_CR18","volume-title":"Gaussian Processes for Machine Learning","author":"CE Rasmussen","year":"2006","unstructured":"Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. The MIT Press, Cambridge (2006)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Ko, J., Klein, D.J., Fox, D., Haehnel, D.: Gaussian processes and reinforcement learning for identification and control of an autonomous blimp. In: Proceedings 2007 IEEE International Conference on Robotics and Automation, pp. 742\u2013747. IEEE, April 2007","DOI":"10.1109\/ROBOT.2007.363075"},{"key":"11_CR20","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/978-3-642-15939-8_30","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"A Wilson","year":"2010","unstructured":"Wilson, A., Fern, A., Tadepalli, P.: Incorporating domain models into Bayesian optimization for RL. In: Balc\u00e1zar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010. LNCS (LNAI), vol. 6323, pp. 467\u2013482. Springer, Heidelberg (2010). \n                      https:\/\/doi.org\/10.1007\/978-3-642-15939-8_30"},{"key":"11_CR21","unstructured":"Engel, Y., Mannor, S., Meir, R.: Bayes meets Bellman: The Gaussian process approach to temporal difference learning. In: Proceedings of the 20th International Conference on Machine Learning, ICML 2003, pp. 154\u2013161 (2003)"},{"issue":"2","key":"11_CR22","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1109\/TPAMI.2013.218","volume":"37","author":"MP Deisenroth","year":"2015","unstructured":"Deisenroth, M.P., Fox, D., Rasmussen, C.E.: Gaussian processes for data-efficient learning in robotics and control. IEEE Trans. Pattern Anal. Mach. Intell. 37(2), 408\u2013423 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"11_CR23","first-page":"1299","volume":"18","author":"DG Matthews","year":"2017","unstructured":"Matthews, D.G., et al.: GPflow: a Gaussian process library using TensorFlow. J. Mach. Learn. Res. 18(1), 1299\u20131304 (2017)","journal-title":"J. Mach. Learn. Res."},{"key":"11_CR24","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint \n                      arXiv:1606.01540\n                      \n                     (2016)"},{"key":"11_CR25","unstructured":"http:\/\/www.ros.org"},{"key":"11_CR26","unstructured":"http:\/\/mlg.eng.cam.ac.uk\/pilco\/"},{"key":"11_CR27","unstructured":"http:\/\/www.incompleteideas.net\/IncIdeas\/BitterLesson.html"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-33274-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,17]],"date-time":"2019-10-17T04:08:54Z","timestamp":1571285334000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-33274-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030332730","9783030332747"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-33274-7_11","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":"14 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}