{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T21:31:32Z","timestamp":1785447092963,"version":"3.56.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9683088","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:50:18Z","timestamp":1643748618000},"page":"2982-2989","source":"Crossref","is-referenced-by-count":16,"title":["Augmented Lagrangian Method for Instantaneously Constrained Reinforcement Learning Problems"],"prefix":"10.1109","author":[{"given":"Jingqi","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Fridovich-Keil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Somayeh","family":"Sojoudi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claire J.","family":"Tomlin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2514\/1.G005066"},{"key":"ref32","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref31","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref30","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":"ref37","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref36","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968293"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487468"},{"key":"ref10","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0316-z"},{"key":"ref12","volume":"7","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref13","article-title":"Constrained reinforcement learning has zero duality gap","author":"paternain","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref15","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"chow","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"ref16","article-title":"A Lyapunov-based approach to safe reinforcement learning","author":"chow","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794107"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460547"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2514\/1.27553"},{"key":"ref4","article-title":"Reinforcement learning of local shape in the game of Go","volume":"7","author":"silver","year":"2007","journal-title":"IJCAI"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-40533-9_11"},{"key":"ref3","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref6","article-title":"Flow: Architecture and benchmarking for reinforcement learning in traffic control","author":"wu","year":"2017"},{"key":"ref29","article-title":"Searching for activation functions","author":"ramachandran","year":"2017"},{"key":"ref5","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref8","article-title":"Provably efficient maximum entropy exploration","author":"hazan","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref7","article-title":"Using confidence bounds for exploitation-exploration tradeoffs","volume":"3","author":"auer","year":"2002","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04191-5_11"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2276"},{"key":"ref22","article-title":"Verifiable reinforcement learning via policy extraction","author":"bastani","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref21","author":"kalweit","year":"2020","journal-title":"Deep constrained Q-learning"},{"key":"ref24","article-title":"IPO: Interior-point policy optimization under constraints","author":"liu","year":"2019"},{"key":"ref23","author":"nocedal","year":"2006","journal-title":"Numerical Optimization"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s001860050035"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","location":"Austin, TX, USA","start":{"date-parts":[[2021,12,14]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09683088.pdf?arnumber=9683088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:58:13Z","timestamp":1652201893000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683088","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}