{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T14:26:44Z","timestamp":1772720804675,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9635984","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"3512-3519","source":"Crossref","is-referenced-by-count":8,"title":["Safe Continuous Control with Constrained Model-Based Policy Optimization"],"prefix":"10.1109","author":[{"given":"Moritz A.","family":"Zanger","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karam","family":"Daaboul","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J.","family":"Marius Zollner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1561\/2200000049","article-title":"Bayesian Reinforcement Learning: A Survey","volume":"8","author":"ghavamzadeh","year":"2015","journal-title":"Foundations and Trends\ufffd in Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2007.4354030"},{"key":"ref11","article-title":"Projection-Based Constrained Policy Optimization","author":"yang","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref12","article-title":"Safe exploration in markov decision processes","author":"moldovan","year":"2012","journal-title":"CoRR"},{"key":"ref13","first-page":"803","article-title":"Lyapunov Design for Safe Reinforcement Learning","volume":"3","author":"perkins","year":"2002","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","article-title":"Safe exploration in continuous action spaces","author":"dalal","year":"2018","journal-title":"CoRR"},{"key":"ref15","article-title":"A Lyapunov-based Approach to Safe Reinforcement Learning","volume":"31","author":"chow","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"1","article-title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","volume":"18","author":"chow","year":"2018","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.02.003"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2926677"},{"key":"ref19","article-title":"Learning-based model predictive control for safe exploration and reinforcement learning","author":"koller","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref27","article-title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","volume":"31","author":"chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"1587","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2017.03.003"},{"key":"ref29","article-title":"Deep Reinforcement Learning and the Deadly Triad","author":"van hasselt","year":"2018"},{"key":"ref5","article-title":"Emergent Tool Use From Multi-Agent Autocurricula","author":"baker","year":"2020","journal-title":"Eighth International Conference on Learning Representations"},{"key":"ref8","first-page":"22","article-title":"Constrained policy optimization","volume":"70","author":"achiam","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref7","first-page":"25","article-title":"Benchmarking Safe Exploration in Deep Reinforcement Learning","author":"ray","year":"2019"},{"key":"ref2","first-page":"1861","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref9","first-page":"1437","article-title":"A Comprehensive Survey on Safe Reinforcement Learning","volume":"16","author":"garc\u00eda","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref1","article-title":"Highdimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref20","article-title":"Safe model-based reinforcement learning with stability guarantees","volume":"30","author":"berkenkamp","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume":"30","author":"lakshminarayanan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Model-Ensemble Trust-Region Policy Optimization","author":"kurutach","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref24","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref23","article-title":"When to Trust Your Model: Model-Based Policy Optimization","volume":"32","author":"janner","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref26","first-page":"1889","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref25","first-page":"267","article-title":"Approximately Optimal Approximate Reinforcement Learning","author":"kakade","year":"2002","journal-title":"Proceedings of the Nineteenth International Conference on Machine Learning"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09635984.pdf?arnumber=9635984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:48Z","timestamp":1652201688000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9635984\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9635984","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}