{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:41:09Z","timestamp":1742917269034,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031703676"},{"type":"electronic","value":"9783031703683"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70368-3_5","type":"book-chapter","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T23:03:11Z","timestamp":1725058991000},"page":"74-91","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamics Adaptive Safe Reinforcement Learning with\u00a0a\u00a0Misspecified Simulator"],"prefix":"10.1007","author":[{"given":"Ruiqi","family":"Xue","sequence":"first","affiliation":[]},{"given":"Ziqian","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Lihe","family":"Li","sequence":"additional","affiliation":[]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yi-Chen","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"5_CR1","unstructured":"Achiam, J., Held, D., Tamar, A., Abbeel, P.: Constrained policy optimization. In: ICML, pp. 22\u201331 (2017)"},{"issue":"7","key":"5_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3543846","volume":"55","author":"MM Afsar","year":"2022","unstructured":"Afsar, M.M., Crump, T., Far, B.: Reinforcement learning based recommender systems: a survey. ACM Comput. Surv. 55(7), 1\u201338 (2022)","journal-title":"ACM Comput. Surv."},{"key":"5_CR3","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223","volume-title":"Constrained Markov Decision Processes","author":"E Altman","year":"2021","unstructured":"Altman, E.: Constrained Markov Decision Processes. Routledge, London (2021)"},{"key":"5_CR4","volume-title":"Mathematical Methods for Physicists: A Comprehensive Guide","author":"GB Arfken","year":"2011","unstructured":"Arfken, G.B., Weber, H.J., Harris, F.E.: Mathematical Methods for Physicists: A Comprehensive Guide. Academic Press, Cambridge (2011)"},{"key":"5_CR5","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1146\/annurev-control-042920-020211","volume":"5","author":"L Brunke","year":"2022","unstructured":"Brunke, L., et al.: Safe learning in robotics: from learning-based control to safe reinforcement learning. Annu. Rev. Control Robot. Auton. Syst. 5, 411\u2013444 (2022)","journal-title":"Annu. Rev. Control Robot. Auton. Syst."},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Chebotar, Y., et al.: Closing the sim-to-real loop: adapting simulation randomization with real world experience. In: ICRA, pp. 8973\u20138979 (2019)","DOI":"10.1109\/ICRA.2019.8793789"},{"issue":"167","key":"5_CR7","first-page":"1","volume":"18","author":"Y Chow","year":"2018","unstructured":"Chow, Y., Ghavamzadeh, M., Janson, L., Pavone, M.: Risk-constrained reinforcement learning with percentile risk criteria. J. Mach. Learn. Res. 18(167), 1\u201351 (2018)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR8","unstructured":"Christiano, P., et al.: Transfer from simulation to real world through learning deep inverse dynamics model. arXiv preprint arXiv:1610.03518 (2016)"},{"key":"5_CR9","unstructured":"Collins, J., Brown, R., Leitner, J., Howard, D.: Traversing the reality gap via simulator tuning. In: ACRA, pp. 1\u201310 (2021)"},{"key":"5_CR10","unstructured":"Desai, S., Durugkar, I., Karnan, H., Warnell, G., Hanna, J., Stone, P.: An imitation from observation approach to transfer learning with dynamics mismatch. In: NeurIPS, pp. 3917\u20133929 (2020)"},{"key":"5_CR11","unstructured":"Eysenbach, B., Asawa, S., Chaudhari, S., Levine, S., Salakhutdinov, R.: Off-dynamics reinforcement learning: training for transfer with domain classifiers. arXiv preprint arXiv:2006.13916 (2020)"},{"key":"5_CR12","unstructured":"Farchy, A., Barrett, S., MacAlpine, P., Stone, P.: Humanoid robots learning to walk faster: from the real world to simulation and back. In: AAMAS, pp. 39\u201346 (2013)"},{"issue":"1","key":"5_CR13","first-page":"1437","volume":"16","author":"J Garc\u0131a","year":"2015","unstructured":"Garc\u0131a, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16(1), 1437\u20131480 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103905","volume":"319","author":"S Gu","year":"2023","unstructured":"Gu, S., et al.: Safe multi-agent reinforcement learning for multi-robot control. Artif. Intell. 319, 103905 (2023)","journal-title":"Artif. Intell."},{"key":"5_CR15","unstructured":"Gu, S., et al.: Multi-agent constrained policy optimisation. arXiv preprint arXiv:2110.02793 (2021)"},{"key":"5_CR16","unstructured":"Guan, C., et al.: Cost-aware offline safe meta reinforcement learning with robust in-distribution online task adaptation. In: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, pp. 743\u2013751 (2024)"},{"key":"5_CR17","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: ICML, pp. 1861\u20131870 (2018)"},{"issue":"2","key":"5_CR18","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1109\/TASE.2021.3064065","volume":"18","author":"S H\u00f6fer","year":"2021","unstructured":"H\u00f6fer, S., et al.: Sim2real in robotics and automation: applications and challenges. IEEE Trans. Autom. Sci. Eng. 18(2), 398\u2013400 (2021)","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"issue":"4\u20135","key":"5_CR19","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."},{"issue":"6","key":"5_CR20","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","volume":"23","author":"BR Kiran","year":"2021","unstructured":"Kiran, B.R., et al.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst. 23(6), 4909\u20134926 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"5_CR21","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative Q-learning for offline reinforcement learning. In: NeurIPS, pp. 1179\u20131191 (2020)"},{"key":"5_CR22","unstructured":"Le, H., Voloshin, C., Yue, Y.: Batch policy learning under constraints. In: ICML, pp. 3703\u20133712 (2019)"},{"key":"5_CR23","unstructured":"Lee, J., et al.: Coptidice: offline constrained reinforcement learning via stationary distribution correction estimation. arXiv preprint arXiv:2204.08957 (2022)"},{"key":"5_CR24","unstructured":"Liu, Z., et al.: Constrained variational policy optimization for safe reinforcement learning. In: ICML, pp. 13644\u201313668 (2022)"},{"key":"5_CR25","unstructured":"Liu, Z., et al.: Constrained decision transformer for offline safe reinforcement learning. arXiv preprint arXiv:2302.07351 (2023)"},{"key":"5_CR26","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"5_CR27","unstructured":"Mehta, B., Diaz, M., Golemo, F., Pal, C.J., Paull, L.: Active domain randomization. In: CoRL, pp. 1162\u20131176. PMLR (2020)"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Mordatch, I., Lowrey, K., Todorov, E.: Ensemble-CIO: full-body dynamic motion planning that transfers to physical humanoids. In: IROS, pp. 5307\u20135314 (2015)","DOI":"10.1109\/IROS.2015.7354126"},{"key":"5_CR29","unstructured":"Nagabandi, A., et al.: Learning to adapt in dynamic, real-world environments through meta-reinforcement learning. In: ICLR (2018)"},{"key":"5_CR30","unstructured":"Niu, H., et al.: When to trust your simulator: dynamics-aware hybrid offline-and-online reinforcement learning. In: NeurIPS, pp. 36599\u201336612 (2022)"},{"key":"5_CR31","unstructured":"Osband, I., Blundell, C., Pritzel, A., Van\u00a0Roy, B.: Deep exploration via bootstrapped DQN. In: NeurIPS, pp. 4026\u20134034 (2016)"},{"key":"5_CR32","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: ICRA, pp. 3803\u20133810 (2018)","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"5_CR33","unstructured":"Ray, A., Achiam, J., Amodei, D.: Benchmarking safe exploration in deep reinforcement learning. arXiv preprint arXiv:1910.01708 (2019)"},{"key":"5_CR34","unstructured":"Ren, A.Z., Dai, H., Burchfiel, B., Majumdar, A.: Adaptsim: task-driven simulation adaptation for sim-to-real transfer. arXiv preprint arXiv:2302.04903 (2023)"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Silver, D., et\u00a0al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","DOI":"10.1038\/nature24270"},{"key":"5_CR36","unstructured":"Stooke, A., Achiam, J., Abbeel, P.: Responsive safety in reinforcement learning by PID Lagrangian methods. In: ICML, pp. 9133\u20139143 (2020)"},{"key":"5_CR37","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"},{"key":"5_CR38","unstructured":"Tessler, C., Mankowitz, D.J., Mannor, S.: Reward constrained policy optimization. arXiv preprint arXiv:1805.11074 (2018)"},{"key":"5_CR39","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: IROS, pp. 23\u201330 (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"5_CR41","unstructured":"Torabi, F., Warnell, G., Stone, P.: Generative adversarial imitation from observation. arXiv preprint arXiv:1807.06158 (2018)"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhan, X., Zhu, X.: Constraints penalized q-learning for safe offline reinforcement learning. In: AAAI, pp. 8753\u20138760 (2022)","DOI":"10.1609\/aaai.v36i8.20855"},{"key":"5_CR43","unstructured":"Yang, T.Y., Rosca, J., Narasimhan, K., Ramadge, P.J.: Projection-based constrained policy optimization. In: ICLR (2019)"},{"key":"5_CR44","unstructured":"Yao, Y., et al.: Constraint-conditioned policy optimization for versatile safe reinforcement learning. In: NeurIPS, vol. 36 (2024)"},{"key":"5_CR45","unstructured":"Yuan, L., Zhang, Z., Li, L., Guan, C., Yu, Y.: A survey of progress on cooperative multi-agent reinforcement learning in open environment. arXiv preprint arXiv:2312.01058 (2023)"},{"issue":"4","key":"5_CR46","first-page":"4396","volume":"45","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Liu, Z., Qiao, Y., Xiang, T., Loy, C.C.: Domain generalization: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4396\u20134415 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70368-3_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T23:09:24Z","timestamp":1725059364000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70368-3_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703676","9783031703683"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70368-3_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}