{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T08:59:21Z","timestamp":1730278761166,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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":[[2019,10]]},"DOI":"10.1109\/itsc.2019.8917113","type":"proceedings-article","created":{"date-parts":[[2019,11,29]],"date-time":"2019-11-29T11:11:50Z","timestamp":1575025910000},"page":"2907-2913","source":"Crossref","is-referenced-by-count":5,"title":["Actor-Critic Reinforcement Learning for Linear Longitudinal Output Control of a Road Vehicle"],"prefix":"10.1109","author":[{"given":"Luca","family":"Puccetti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Rathgeber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soren","family":"Hohmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"mnih","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref31","article-title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","author":"salimans","year":"2016","journal-title":"Advances in Neural Information Processing Systems 29 (NIPS 2016)"},{"year":"2011","author":"lyons","journal-title":"Understanding Digital Signal Processing","key":"ref30"},{"key":"ref10","article-title":"Unsupervised Predictive Memory in a Goal-Directed Agent","author":"wayne","year":"2018","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/TAC.1970.1099363"},{"year":"2018","author":"sutton","journal-title":"Reinforcement Learning An Introduction Adaptive Computation and Machine Learning","key":"ref12"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1007\/BFb0067700"},{"key":"ref14","article-title":"On the difficulty of training Recurrent Neural Networks","author":"pascanu","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"year":"2017","author":"harb","article-title":"Investigating Recurrence and Eligibility Traces in Deep Q-Networks","key":"ref15"},{"key":"ref16","article-title":"Deterministic Policy Gradient Algorithms","author":"silver","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning"},{"key":"ref17","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"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1016\/B978-1-55860-335-6.50042-8"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1357","DOI":"10.1016\/0005-1098(95)00048-2","article-title":"A Necessary and Sufficient Condition for Output Feedback Stabilizability","volume":"31","author":"ku?era","year":"1995","journal-title":"Automatica"},{"year":"2015","author":"hausknecht","article-title":"Deep Recurrent Q-Learning for Partially Observable MDPs","key":"ref28"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/IVS.2008.4621222"},{"year":"2015","author":"heess","article-title":"Memory-based control with recurrent neural networks","key":"ref27"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/FBIT.2007.37"},{"key":"ref6","first-page":"987","article-title":"A Reinforcement Learning Approach to Optimize the Longitudinal Behavior of a Partial Autonomous Driving Assistance System","volume":"242","author":"pietquinn","year":"2012","journal-title":"Frontiers in Artificial Intelligence and Applications"},{"year":"1997","author":"ogata","journal-title":"Modern Control Engineering","key":"ref29"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TITS.2011.2157145"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICIST.2015.7288976"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TCST.2013.2271276"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1049\/cp:19960708"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ITSC.2018.8569977"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref20","first-page":"1057","article-title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation","author":"sutton","year":"1999","journal-title":"NIPS’99 Proceedings of the 12th International Conference on Neural Information Processing Systems"},{"key":"ref22","article-title":"Learning Policies with External Memory","author":"peshkin","year":"1999","journal-title":"Machine Learning"},{"year":"2000","author":"sutton","article-title":"Comparing Policy-Gradient Algorithms","key":"ref21"},{"year":"2012","author":"ljung","journal-title":"System Identification Theory for the User","key":"ref24"},{"key":"ref23","first-page":"271","article-title":"Reinforcement Learning With Hidden States","volume":"2","author":"lin","year":"1993","journal-title":"From Animals to Animats 2"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ECC.2015.7330913"},{"year":"2017","author":"dean","article-title":"On the Sample Complexity of the Linear Quadratic Regulator","key":"ref25"}],"event":{"name":"2019 IEEE Intelligent Transportation Systems Conference - ITSC","start":{"date-parts":[[2019,10,27]]},"location":"Auckland, New Zealand","end":{"date-parts":[[2019,10,30]]}},"container-title":["2019 IEEE Intelligent Transportation Systems Conference (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8907344\/8916833\/08917113.pdf?arnumber=8917113","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:44:05Z","timestamp":1658155445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8917113\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/itsc.2019.8917113","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}