{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T14:10:09Z","timestamp":1755871809635,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T00:00:00Z","timestamp":1704326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,4]]},"DOI":"10.1145\/3632410.3632446","type":"proceedings-article","created":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T18:15:16Z","timestamp":1704305716000},"page":"100-108","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Model-based Safe Reinforcement Learning using Variable Horizon Rollouts"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5825-2394","authenticated-orcid":false,"given":"Shourya","family":"Gupta","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Ropar, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0869-7193","authenticated-orcid":false,"given":"Utkarsh","family":"Suryaman","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Ropar, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0277-4484","authenticated-orcid":false,"given":"Rahul","family":"Narava","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Ropar, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1375-2266","authenticated-orcid":false,"given":"Shashi Shekhar","family":"Jha","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Ropar, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,1,4]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Felix Berkenkamp Matteo Turchetta Angela\u00a0P. Schoellig and Andreas Krause. 2017. Safe Model-based Reinforcement Learning with Stability Guarantees. (2017)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"e_1_3_2_1_3_1","volume-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models. Advances in neural information processing systems 31","author":"Chua Kurtland","year":"2018","unstructured":"Kurtland Chua, Roberto Calandra, Rowan McAllister, and Sergey Levine. 2018. Deep reinforcement learning in a handful of trials using probabilistic dynamics models. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_4_1","volume-title":"Safe exploration in continuous action spaces. arXiv preprint arXiv:1801.08757","author":"Dalal Gal","year":"2018","unstructured":"Gal Dalal, Krishnamurthy Dvijotham, Matej Vecerik, Todd Hester, Cosmin Paduraru, and Yuval Tassa. 2018. Safe exploration in continuous action spaces. arXiv preprint arXiv:1801.08757 (2018)."},{"key":"e_1_3_2_1_5_1","first-page":"1","article-title":"A Comprehensive Survey on Safe Reinforcement Learning","volume":"21","author":"Garc\u00eda Javier","year":"2020","unstructured":"Javier Garc\u00eda and Fernando Fern\u00e1ndez. 2020. A Comprehensive Survey on Safe Reinforcement Learning. Journal of Machine Learning Research 21 (2020), 1\u201360.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_6_1","volume-title":"Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Kristian Hartikainen, George Tucker, Sehoon Ha, Jie Tan, Vikash Kumar, Henry Zhu, Abhishek Gupta, Pieter Abbeel, 2018. Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)."},{"key":"e_1_3_2_1_7_1","volume-title":"When to trust your model: Model-based policy optimization. Advances in neural information processing systems 32","author":"Janner Michael","year":"2019","unstructured":"Michael Janner, Justin Fu, Marvin Zhang, and Sergey Levine. 2019. When to trust your model: Model-based policy optimization. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_8_1","volume-title":"Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm. arXiv preprint arXiv:2103.07083","author":"Jayant Ashish\u00a0Kumar","year":"2021","unstructured":"Ashish\u00a0Kumar Jayant and Shalabh Bhatnagar. 2021. Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm. arXiv preprint arXiv:2103.07083 (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"Model-ensemble trust-region policy optimization. arXiv preprint arXiv:1802.10592","author":"Kurutach Thanard","year":"2018","unstructured":"Thanard Kurutach, Ignasi Clavera, Yan Duan, Aviv Tamar, and Pieter Abbeel. 2018. Model-ensemble trust-region policy optimization. arXiv preprint arXiv:1802.10592 (2018)."},{"key":"e_1_3_2_1_10_1","volume-title":"Algorithmic framework for model-based deep reinforcement learning with theoretical guarantees. arXiv preprint arXiv:1807.03858","author":"Luo Yuping","year":"2018","unstructured":"Yuping Luo, Huazhe Xu, Yuanzhi Li, Yuandong Tian, Trevor Darrell, and Tengyu Ma. 2018. Algorithmic framework for model-based deep reinforcement learning with theoretical guarantees. arXiv preprint arXiv:1807.03858 (2018)."},{"key":"e_1_3_2_1_11_1","unstructured":"Carl\u00a0Edward Rasmussen and Malte Kuss. 2003. Gaussian Processes in Reinforcement Learning. (2003)."},{"key":"e_1_3_2_1_12_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton S.","year":"2018","unstructured":"Richard\u00a0S. Sutton and Andrew\u00a0G. Barto. 2018. Reinforcement Learning: An Introduction. The MIT Press."},{"volume-title":"Algorithms for Reinforcement Learning","author":"Szepesv\u00e1ri Csaba","key":"e_1_3_2_1_13_1","unstructured":"Csaba Szepesv\u00e1ri. 2010. Algorithms for Reinforcement Learning. Morgan & Claypool Publishers."},{"key":"e_1_3_2_1_14_1","first-page":"13859","article-title":"Safe reinforcement learning by imagining the near future","volume":"34","author":"Thomas Garrett","year":"2021","unstructured":"Garrett Thomas, Yuping Luo, and Tengyu Ma. 2021. Safe reinforcement learning by imagining the near future. Advances in Neural Information Processing Systems 34 (2021), 13859\u201313869.","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Safe Reinforcement Learning. Ph.\u00a0D. Dissertation","author":"Thomas S.","key":"e_1_3_2_1_15_1","unstructured":"P.\u00a0S. Thomas. 2015. Safe Reinforcement Learning. Ph.\u00a0D. Dissertation. University of Massachusetts, Amherst."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Machine Learning. PMLR, 9797\u20139806","author":"Wachi Akifumi","year":"2020","unstructured":"Akifumi Wachi and Yanan Sui. 2020. Safe reinforcement learning in constrained Markov decision processes. In International Conference on Machine Learning. PMLR, 9797\u20139806."},{"key":"e_1_3_2_1_18_1","volume-title":"Exploring model-based planning with policy networks. arXiv preprint arXiv:1906.08649","author":"Wang Tingwu","year":"2019","unstructured":"Tingwu Wang and Jimmy Ba. 2019. Exploring model-based planning with policy networks. arXiv preprint arXiv:1906.08649 (2019)."},{"key":"e_1_3_2_1_19_1","volume-title":"Cup: A conservative update policy algorithm for safe reinforcement learning. arXiv preprint arXiv:2202.07565","author":"Yang Long","year":"2022","unstructured":"Long Yang, Jiaming Ji, Juntao Dai, Yu Zhang, Pengfei Li, and Gang Pan. 2022. Cup: A conservative update policy algorithm for safe reinforcement learning. arXiv preprint arXiv:2202.07565 (2022)."},{"key":"e_1_3_2_1_20_1","first-page":"15338","article-title":"First order constrained optimization in policy space","volume":"33","author":"Zhang Yiming","year":"2020","unstructured":"Yiming Zhang, Quan Vuong, and Keith Ross. 2020. First order constrained optimization in policy space. Advances in Neural Information Processing Systems 33 (2020), 15338\u201315349.","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"CODS-COMAD 2024: 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","acronym":"CODS-COMAD 2024","location":"Bangalore India"},"container-title":["Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3632410.3632446","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3632410.3632446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:36:59Z","timestamp":1755869819000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3632410.3632446"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,4]]},"references-count":20,"alternative-id":["10.1145\/3632410.3632446","10.1145\/3632410"],"URL":"https:\/\/doi.org\/10.1145\/3632410.3632446","relation":{},"subject":[],"published":{"date-parts":[[2024,1,4]]},"assertion":[{"value":"2024-01-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}