{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T08:52:29Z","timestamp":1742979149983,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031152252"},{"type":"electronic","value":"9783031152269"}],"license":[{"start":{"date-parts":[[2022,8,25]],"date-time":"2022-08-25T00:00:00Z","timestamp":1661385600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,8,25]],"date-time":"2022-08-25T00:00:00Z","timestamp":1661385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-15226-9_17","type":"book-chapter","created":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T03:27:47Z","timestamp":1661311667000},"page":"155-166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bridging the\u00a0Reality Gap via\u00a0Progressive Bayesian Optimisation"],"prefix":"10.1007","author":[{"given":"Chen","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andre","family":"Rosendo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,25]]},"reference":[{"key":"17_CR1","unstructured":"Schrittwieser, J., Hubert, T., Mandhane, A., Barekatain, M., Antonoglou, I., Silver, D.: Online and offline reinforcement learning by planning with a learned model. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"issue":"1","key":"17_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12984-021-00919-y","volume":"18","author":"S Song","year":"2021","unstructured":"Song, S., et al.: Deep reinforcement learning for modeling human locomotion control in neuromechanical simulation. J. Neuroeng. Rehabil. 18(1), 1\u201317 (2021)","journal-title":"J. Neuroeng. Rehabil."},{"issue":"4\u20135","key":"17_CR3","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1177\/0278364920987859","volume":"40","author":"J Ibarz","year":"2021","unstructured":"Ibarz, J., Tan, J., Finn, C., Kalakrishnan, M., Pastor, P., Levine, S.: How to train your robot with deep reinforcement learning: lessons we have learned. Int. J. Robot. Res. 40(4\u20135), 698\u2013721 (2021)","journal-title":"Int. J. Robot. Res."},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Peng, X.B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Sim-to-real transfer of robotic control with dynamics randomization. In: 2018 IEEE international conference on robotics and automation (ICRA), pp. 3803\u20133810. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"17_CR5","unstructured":"Collins, J., Brown, R., Leitner, J., Howard, D.: Follow the gradient: crossing the reality gap using differentiable physics (realitygrad). arXiv preprint arXiv:2109.04674 (2021)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 23\u201330. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"17_CR7","unstructured":"James, S., Davison, A.J., Johns, E.: Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task. In: Conference on Robot Learning, pp. 334\u2013343. PMLR (2017)"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Borrego, J., Figueiredo, R., Dehban, A., Moreno, P., Bernardino, A., Santos-Victor, J.: A generic visual perception domain randomisation framework for gazebo. In: 2018 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), pp. 237\u2013242. IEEE (2018)","DOI":"10.1109\/ICARSC.2018.8374189"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Tan, J., et al.: Sim-to-real: learning agile locomotion for quadruped robots. arXiv preprint arXiv:1804.10332 (2018)","DOI":"10.15607\/RSS.2018.XIV.010"},{"issue":"26","key":"17_CR10","doi-asserted-by":"publisher","first-page":"eaau5872","DOI":"10.1126\/scirobotics.aau5872","volume":"4","author":"J Hwangbo","year":"2019","unstructured":"Hwangbo, J., et al.: Learning agile and dynamic motor skills for legged robots. Sci. Robot. 4(26), eaau5872 (2019)","journal-title":"Sci. Robot."},{"key":"17_CR11","doi-asserted-by":"publisher","unstructured":"Siekmann, J., et al.: Learning memory-based control for human-scale bipedal locomotion. In: M. Toussaint, A. Bicchi, T. Hermans (eds.) Robotics: Science and Systems XVI, Virtual Event\/Corvalis, Oregon, USA, 12\u201316 July 2020 (2020). https:\/\/doi.org\/10.15607\/RSS.2020.XVI.031","DOI":"10.15607\/RSS.2020.XVI.031"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Kolev, S., Todorov, E.: Physically consistent state estimation and system identification for contacts. In: 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), pp. 1036\u20131043. IEEE (2015)","DOI":"10.1109\/HUMANOIDS.2015.7363481"},{"key":"17_CR13","doi-asserted-by":"publisher","unstructured":"Ramos, F., Possas, R., Fox, D.: BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators. In: Proceedings of Robotics: Science and Systems. FreiburgimBreisgau, Germany (2019). https:\/\/doi.org\/10.15607\/RSS.2019.XV.029","DOI":"10.15607\/RSS.2019.XV.029"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Chebotar, Y., et al.: Closing the sim-to-real loop: adapting simulation randomization with real world experience. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 8973\u20138979. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"17_CR15","doi-asserted-by":"publisher","unstructured":"Yu, W., Tan, J., Liu, C.K., Turk, G.: Preparing for the unknown: learning a universal policy with online system identification. In: Amato, N.M., Srinivasa, S.S., Ayanian, N., Kuindersma, S. (eds.) Robotics: Science and Systems XIII, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA, 12\u201316 July 2017 (2017). https:\/\/doi.org\/10.15607\/RSS.2017.XIII.048. http:\/\/www.roboticsproceedings.org\/rss13\/p48.html","DOI":"10.15607\/RSS.2017.XIII.048"},{"key":"17_CR16","unstructured":"Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"key":"17_CR17","unstructured":"Antonova, R., Rai, A., Li, T., Kragic, D.: Bayesian optimization in variational latent spaces with dynamic compression. In: Conference on Robot Learning, pp. 456\u2013465. PMLR (2020)"},{"key":"17_CR18","unstructured":"M\u00fcller, S., von Rohr, A., Trimpe, S.: Local policy search with Bayesian optimization. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Katz, B., Di Carlo, J., Kim, S.: Mini cheetah: a platform for pushing the limits of dynamic quadruped control. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 6295\u20136301. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793865"},{"issue":"4","key":"17_CR20","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1023\/A:1008202821328","volume":"11","author":"R Storn","year":"1997","unstructured":"Storn, R., Price, K.: Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim. 11(4), 341\u2013359 (1997)","journal-title":"J. Global Optim."},{"key":"17_CR21","unstructured":"Collins, J., Brown, R., Leitner, J., Howard, D.: Traversing the reality gap via simulator tuning. arXiv preprint arXiv:2003.01369 (2020)"},{"key":"17_CR22","unstructured":"Srinivas, N., Krause, A., Kakade, S., Seeger, M.: Gaussian process optimization in the bandit setting: no regret and experimental design. In: Proceedings of the 27th International Conference on International Conference on Machine Learning, ICML 2010, pp. 1015\u20131022. Omnipress, Madison (2010)"},{"key":"17_CR23","unstructured":"Coumans, E., Bai, Y.: Pybullet, a python module for physics simulation for games, robotics and machine learning (2016)"},{"key":"17_CR24","unstructured":"Rajeswaran, A., Ghotra, S., Ravindran, B., Levine, S.: EPOpt: learning robust neural network policies using model ensembles. In: 5th International Conference on Learning Representations. OpenReview.net (2017)"},{"key":"17_CR25","doi-asserted-by":"publisher","unstructured":"Tan, J., et al.: Sim-to-real: learning agile locomotion for quadruped robots. In: Proceedings of Robotics: Science and Systems, Pittsburgh, Pennsylvania (2018). https:\/\/doi.org\/10.15607\/RSS.2018.XIV.010","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Tassa, Y., Erez, T., Todorov, E.: Synthesis and stabilization of complex behaviors through online trajectory optimization. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 4906\u20134913. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386025"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Huang, A.S., Olson, E., Moore, D.C.: LCM: lightweight communications and marshalling. In: 2010 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 4057\u20134062. IEEE (2010)","DOI":"10.1109\/IROS.2010.5649358"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Auger, A., Hansen, N.: Tutorial CMA-ES: evolution strategies and covariance matrix adaptation. In: Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation, pp. 827\u2013848 (2012)","DOI":"10.1145\/2330784.2330919"},{"key":"17_CR29","doi-asserted-by":"publisher","unstructured":"Le\u00a0Goff, L.K., et al.: Sample and time efficient policy learning with CMA-ES and Bayesian Optimisation. In: ALIFE 2020: The 2020 Conference on Artificial Life, pp. 432\u2013440 (2020). https:\/\/doi.org\/10.1162\/isal_a_00299","DOI":"10.1162\/isal_a_00299"},{"key":"17_CR30","unstructured":"Lim, V., et al.: Planar robot casting with real2sim2real self-supervised learning. In: 2022 International Conference on Robotics and Automation (ICRA). IEEE (2022)"}],"container-title":["Lecture Notes in Networks and Systems","Robotics in Natural Settings"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-15226-9_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T03:35:48Z","timestamp":1661312148000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-15226-9_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,25]]},"ISBN":["9783031152252","9783031152269"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-15226-9_17","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2022,8,25]]},"assertion":[{"value":"25 August 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CLAWAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Climbing and Walking Robots Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ponta Delgada","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"clawar2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/clawar.org\/clawar2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}