{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T01:54:38Z","timestamp":1778810078867,"version":"3.51.4"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197200","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"10681-10687","source":"Crossref","is-referenced-by-count":5,"title":["Dynamic Actor-Advisor Programming for Scalable Safe Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Lingwei","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunduan","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"3207","article-title":"Dynamic policy programming","volume":"13","author":"azar","year":"2012","journal-title":"J Machine Learning Research (JMLR)"},{"key":"ref11","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","author":"kakade","year":"2002","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref12","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 (JMLR)"},{"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","first-page":"1451","article-title":"Safe exploration in markov decision processes","author":"moldovan","year":"2012","journal-title":"International Coference on International Conference on Machine Learning (ICML)"},{"key":"ref15","first-page":"3042","article-title":"Optimizing over a restricted policy class in mdps","volume":"89","author":"banijamali","year":"2019","journal-title":"Machine Learning Research"},{"key":"ref16","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.06.007"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.11.004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref6","first-page":"1","article-title":"A Lyapunov-based Approach to Safe Reinforcement Learning","author":"chow","year":"2018","journal-title":"Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref5","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"berkenkamp","year":"2017","journal-title":"Proc of Neural Information Processing Systems (NIPS)"},{"key":"ref8","article-title":"Combating reinforcement learning’s sisyphean curse with intrinsic fear","author":"lipton","year":"2016","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3761"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref9","first-page":"1","article-title":"Leave no trace: Learning to reset for safe and autonomous reinforcement learning","author":"eysenbach","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref20","article-title":"The actor-advisor: Policy gradient with off-policy advice","author":"plisnier","year":"2019","journal-title":"CoRR"},{"key":"ref22","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","first-page":"1431","article-title":"Action-constrained Markov Decision Processes with Kullback-Leibler cost","volume":"75","author":"bu\u0161i?","year":"2018","journal-title":"Proceedings of the 31st Conference On Learning Theory"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197200.pdf?arnumber=9197200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:15:12Z","timestamp":1656375312000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197200\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197200","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}