{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T15:44:50Z","timestamp":1773935090521,"version":"3.50.1"},"reference-count":39,"publisher":"Informa UK Limited","issue":"4","funder":[{"name":"The United States National Science Foundation","award":["#1762595"],"award-info":[{"award-number":["#1762595"]}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Control"],"published-print":{"date-parts":[[2023,4,3]]},"DOI":"10.1080\/00207179.2022.2029945","type":"journal-article","created":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T17:28:11Z","timestamp":1642440491000},"page":"1079-1090","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":9,"title":["Safe control of nonlinear systems in LPV framework using model-based reinforcement learning"],"prefix":"10.1080","volume":"96","author":[{"given":"Yajie","family":"Bao","sequence":"first","affiliation":[{"name":"School of Electrical & Computer Engineering, The University of Georgia, Athens, GA, USA"}]},{"given":"Javad","family":"Mohammadpour Velni","sequence":"additional","affiliation":[{"name":"School of Electrical & Computer Engineering, The University of Georgia, Athens, GA, USA"}]}],"member":"301","published-online":{"date-parts":[[2022,1,27]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2013.05.008"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039601"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.23919\/ECC54610.2021.9655004"},{"key":"e_1_3_3_5_1","first-page":"5286","volume-title":"IFAC-PapersOnLine","author":"Bao Y.","year":"2020","unstructured":"Bao, Y., Velni, J. M., Basina, A., & Shahbakhti, M. (2020). IFAC-PapersOnLine (Vol. 53.2, pp. 5286\u20135291). IFAC."},{"key":"e_1_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2020-3210"},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.7782633"},{"key":"e_1_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814855"},{"key":"e_1_3_3_9_1","volume-title":"Advances in Neural Information Processing Systems (pp. 908\u2013918)","author":"Berkenkamp F.","year":"2017","unstructured":"Berkenkamp, F., Turchetta, M., Schoellig, A., & Krause, A. (2017). Safe model-based reinforcement learning with stability guarantees. Advances in Neural Information Processing Systems (pp. 908\u2013918).\u00a0NeurIPS."},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"e_1_3_3_11_1","volume-title":"International Conference on Machine Learning (pp. 1613\u20131622)","author":"Blundell C.","year":"2015","unstructured":"Blundell, C., Cornebise, J., Kavukcuoglu, K., & Wierstra, D. (2015). Weight uncertainty in neural network. International Conference on Machine Learning (pp. 1613\u20131622).\u00a0ICML."},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431275"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"e_1_3_3_14_1","unstructured":"Chollet F. (2015). Keras. https:\/\/keras.io."},{"key":"e_1_3_3_15_1","unstructured":"Clevert D. A. Unterthiner T. & Hochreiter S. (2015). Fast and accurate deep network learning by exponential linear units (ELUS). arXiv preprint arXiv:1511.07289."},{"key":"e_1_3_3_16_1","volume-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11) (pp. 465\u2013472)","author":"Deisenroth M.","year":"2011","unstructured":"Deisenroth, M., & Rasmussen, C. E. (2011). PILCO: A model-based and data-efficient approach to policy search. Proceedings of the 28th International Conference on Machine Learning (ICML-11) (pp. 465\u2013472).\u00a0ICML."},{"key":"e_1_3_3_17_1","volume-title":"A survey on policy search for robotics","author":"Deisenroth M. P.","year":"2013","unstructured":"Deisenroth, M. P., Neumann, G., & Peters, J. (2013). A survey on policy search for robotics. Now Publishers."},{"key":"e_1_3_3_18_1","volume-title":"Data-Efficient Machine Learning Workshop, ICML (Vol. 4, p. 34)","author":"Gal Y.","year":"2016","unstructured":"Gal, Y., McAllister, R., & Rasmussen, C. E. (2016). Improving PILCO with Bayesian neural network dynamics models. Data-Efficient Machine Learning Workshop, ICML (Vol. 4, p. 34).\u00a0ICML."},{"key":"e_1_3_3_19_1","unstructured":"Gros S. & Zanon M. (2020). Safe reinforcement learning with stability & safety guarantees using robust MPC. arXiv preprint arXiv:2012.07369."},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2276"},{"key":"e_1_3_3_21_1","unstructured":"Hanema J. (2018). Anticipative model predictive control for linear parameter-varying systems [Unpublished doctoral dissertation]. Technische Universiteit Eindhoven."},{"key":"e_1_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.108622"},{"key":"e_1_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7_7"},{"key":"e_1_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1146\/control.2020.3.issue-1"},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594018"},{"key":"e_1_3_3_26_1","volume-title":"Advances in Neural Information Processing Systems (pp. 12519\u201312530)","author":"Janner M.","year":"2019","unstructured":"Janner, M., Fu, J., Zhang, M., & Levine, S. (2019). When to trust your model: Model-based policy optimization. Advances in Neural Information Processing Systems (pp. 12519\u201312530).\u00a0NeurIPS."},{"key":"e_1_3_3_27_1","article-title":"Deep variational Bayes filters: Unsupervised learning of state space models from raw data","author":"Karl M.","year":"2016","unstructured":"Karl, M., Soelch, M., Bayer, J., & van der Smagt, P. (2016). Deep variational Bayes filters: Unsupervised learning of state space models from raw data. arXiv preprint arXiv:1605.06432.","journal-title":"arXiv preprint arXiv:1605.06432"},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"e_1_3_3_29_1","unstructured":"Lillicrap T. P. Hunt J. J. Pritzel A. Heess N. Erez T. Tassa Y. Silver D. & Wierstra D. (2015). Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971."},{"key":"e_1_3_3_30_1","unstructured":"Mnih V. Kavukcuoglu K. Silver D. Graves A. Antonoglou I. Wierstra D. & Riedmiller M. (2013). Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602."},{"key":"e_1_3_3_31_1","unstructured":"Padakandla S. (2020). A survey of reinforcement learning algorithms for dynamically varying environments. arXiv preprint arXiv:2005.10619."},{"key":"e_1_3_3_32_1","volume-title":"Manual for model 750: Control moment gyroscope","author":"Parks T. R.","year":"1999","unstructured":"Parks, T. R. (1999). Manual for model 750: Control moment gyroscope. Educational Control Products."},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"e_1_3_3_34_1","article-title":"Generalised Pinsker inequalities","author":"Reid M. D.","year":"2009","unstructured":"Reid, M. D., & Williamson, R. C. (2009). Generalised Pinsker inequalities. arXiv preprint arXiv:0906.1244.","journal-title":"arXiv preprint arXiv:0906.1244"},{"key":"e_1_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.11.004"},{"key":"e_1_3_3_36_1","volume-title":"International Conference on Machine Learning (pp. 387\u2013395)","author":"Silver D.","year":"2014","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., & Riedmiller, M. (2014). Deterministic policy gradient algorithms. International Conference on Machine Learning (pp. 387\u2013395).\u00a0ICML."},{"key":"e_1_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw1975"},{"key":"e_1_3_3_38_1","unstructured":"Tran D. Dusenberry M. W. van der Wilk M. & Hafner D. (2018). Bayesian layers: A module for neural network uncertainty. CoRR abs\/1812.03973. http:\/\/arxiv.org\/abs\/1812.03973"},{"key":"e_1_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"e_1_3_3_40_1","volume-title":"Advances in Neural Information Processing Systems (pp. 3127\u20133139)","author":"Yu M.","year":"2019","unstructured":"Yu, M., Yang, Z., Kolar, M., & Wang, Z. (2019). Convergent policy optimization for safe reinforcement learning. Advances in Neural Information Processing Systems (pp. 3127\u20133139).\u00a0NeurIPS."}],"container-title":["International Journal of Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207179.2022.2029945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T12:50:03Z","timestamp":1725022203000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207179.2022.2029945"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,27]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4,3]]}},"alternative-id":["10.1080\/00207179.2022.2029945"],"URL":"https:\/\/doi.org\/10.1080\/00207179.2022.2029945","relation":{},"ISSN":["0020-7179","1366-5820"],"issn-type":[{"value":"0020-7179","type":"print"},{"value":"1366-5820","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,27]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tcon20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tcon20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2021-02-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}