{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T02:48:51Z","timestamp":1730342931922,"version":"3.28.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,29]]},"DOI":"10.23919\/ecc54610.2021.9654962","type":"proceedings-article","created":{"date-parts":[[2022,1,3]],"date-time":"2022-01-03T15:17:44Z","timestamp":1641223064000},"page":"1086-1091","source":"Crossref","is-referenced-by-count":1,"title":["Bias Correction in Deterministic Policy Gradient Using Robust MPC"],"prefix":"10.23919","author":[{"given":"Arash Bahari","family":"Kordabad","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hossein","family":"Nejatbakhsh Esfahani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastien","family":"Gros","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Reinforcement learning based on MPC\/MHE for unmodeled and partially observable dynamics","year":"2021","author":"nejatbakhsh esfahani","key":"ref10"},{"key":"ref11","volume":"2","author":"rawlings","year":"2017","journal-title":"Model Predictive Control Theory Computation and Design"},{"key":"ref12","article-title":"Safe reinforcement learning using robust MPC","author":"zanon","year":"2020","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref13","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483016"},{"article-title":"Safe exploration of nonlinear dynamical systems: A predictive safety filter for reinforcement learning","year":"2018","author":"wabersich","key":"ref4"},{"key":"ref3","first-page":"i?387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2913768"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483100"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.1195"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref2"},{"journal-title":"REINFORCEMENT LEARNING AND OPTIMAL CONTROL","year":"2019","author":"bertsekas","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.1196"}],"event":{"name":"2021 European Control Conference (ECC)","start":{"date-parts":[[2021,6,29]]},"location":"Delft, Netherlands","end":{"date-parts":[[2021,7,2]]}},"container-title":["2021 European Control Conference (ECC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9654796\/9654428\/09654962.pdf?arnumber=9654962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,8]],"date-time":"2022-03-08T16:57:30Z","timestamp":1646758650000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9654962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,29]]},"references-count":14,"URL":"https:\/\/doi.org\/10.23919\/ecc54610.2021.9654962","relation":{},"subject":[],"published":{"date-parts":[[2021,6,29]]}}}