{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:34:43Z","timestamp":1768340083090,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1109\/cdc57313.2025.11312015","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"942-947","source":"Crossref","is-referenced-by-count":1,"title":["MAD: A Magnitude And Direction Policy Parametrization for Stability Constrained Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Luca","family":"Furieri","sequence":"first","affiliation":[{"name":"École Polytechnique Fédérale de Lausanne (EPFL),Institute of Mechanical Engineering"}]},{"given":"Sucheth","family":"Shenoy","sequence":"additional","affiliation":[{"name":"École Polytechnique Fédérale de Lausanne (EPFL),Institute of Mechanical Engineering"}]},{"given":"Danilo","family":"Saccani","sequence":"additional","affiliation":[{"name":"École Polytechnique Fédérale de Lausanne (EPFL),Institute of Mechanical Engineering"}]},{"given":"Andrea","family":"Martin","sequence":"additional","affiliation":[{"name":"École Polytechnique Fédérale de Lausanne (EPFL),Institute of Mechanical Engineering"}]},{"given":"Giancarlo","family":"Ferrari-Trecate","sequence":"additional","affiliation":[{"name":"École Polytechnique Fédérale de Lausanne (EPFL),Institute of Mechanical Engineering"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref4","article-title":"Actor-critic algorithms","volume":"12","author":"Konda","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref6","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International conference on machine learning","author":"Silver"},{"key":"ref7","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref8","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"International Conference on Machine Learning","author":"Fazel"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref10","article-title":"Provably global convergence of actor-critic: A case for linear quadratic regulator with ergodic cost","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/ACC53348.2022.9867476"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967370"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992492"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/OJCSYS.2024.3441768"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2024.111642"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2024.3382376"},{"key":"ref18","volume-title":"Reinforcement learning and optimal control.","author":"Bertsekas","year":"2019"},{"key":"ref19","article-title":"Memory-based control with recurrent neural networks","author":"Heess","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(00)00023-6"},{"key":"ref21","first-page":"26670","article-title":"Resurrecting recurrent neural networks for long sequences","volume-title":"International Conference on Machine Learning","author":"Orvieto"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3184847"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1109\/CDC57313.2025.11312015","article-title":"MAD: A magnitude and direction policy parametrization for stability constrained reinforcement learning","author":"Furieri","year":"2025"}],"event":{"name":"2025 IEEE 64th Conference on Decision and Control (CDC)","location":"Rio de Janeiro, Brazil","start":{"date-parts":[[2025,12,9]]},"end":{"date-parts":[[2025,12,12]]}},"container-title":["2025 IEEE 64th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11311984\/11311968\/11312015.pdf?arnumber=11312015","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:49:46Z","timestamp":1768294186000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312015\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312015","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}