{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T15:46:56Z","timestamp":1768319216672,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/cdc40024.2019.9030185","type":"proceedings-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T00:43:11Z","timestamp":1584060191000},"page":"7110-7115","source":"Crossref","is-referenced-by-count":4,"title":["Model predictive control with stage cost shaping inspired by reinforcement learning"],"prefix":"10.1109","author":[{"given":"Lukas","family":"Beckenbach","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Osinenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Streif","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","author":"khalil","year":"1996","journal-title":"Nonlinear Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref12","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"arXiv 1509 02971 [cs LG]"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1989.4790360"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/S0005-1098(99)00214-9","article-title":"Constrained model predictive control: Stability and optimality","volume":"36","author":"mayne","year":"2000","journal-title":"Automatica"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1111\/j.1934-6093.1999.tb00002.x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3182\/20110828-6-IT-1002.00609"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2753460"},{"key":"ref18","volume":"37","author":"rummery","year":"1994","journal-title":"On-line Q-learning using connectionist systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(00)00084-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992701"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.927799"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/070707853"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.846597"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/9.995049"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(98)00073-9"},{"key":"ref1","volume":"ii","author":"bertsekas","year":"2012","journal-title":"Dynamic Programming and Optimal Control Approximate Dynamic Programming"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2001.946385"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2006.1655466"},{"key":"ref23","article-title":"Safe reinforcement learning using robust MPC","author":"zanon","year":"2019","journal-title":"arXiv 1906 04005v1 [cs SY]"}],"event":{"name":"2019 IEEE 58th Conference on Decision and Control (CDC)","location":"Nice, France","start":{"date-parts":[[2019,12,11]]},"end":{"date-parts":[[2019,12,13]]}},"container-title":["2019 IEEE 58th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8977134\/9028853\/09030185.pdf?arnumber=9030185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T16:25:47Z","timestamp":1658247947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9030185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cdc40024.2019.9030185","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}