%0 Conference Paper %1 conf/l4dc/AmosSYW21 %A Amos, Brandon %A Stanton, Samuel %A Yarats, Denis %A Wilson, Andrew Gordon %B L4DC %D 2021 %E Jadbabaie, Ali %E Lygeros, John %E Pappas, George J. %E Parrilo, Pablo A. %E Recht, Benjamin %E Tomlin, Claire J. %E Zeilinger, Melanie N. %I PMLR %K dblp %P 6-20 %T On the model-based stochastic value gradient for continuous reinforcement learning. %U http://dblp.uni-trier.de/db/conf/l4dc/l4dc2021.html#AmosSYW21 %V 144

@inproceedings{conf/l4dc/AmosSYW21, added-at = {2021-06-14T00:00:00.000+0200}, author = {Amos, Brandon and Stanton, Samuel and Yarats, Denis and Wilson, Andrew Gordon}, biburl = {https://www.bibsonomy.org/bibtex/2347118ec4d9779b06a76823f116dd6c5/dblp}, booktitle = {L4DC}, crossref = {conf/l4dc/2021}, editor = {Jadbabaie, Ali and Lygeros, John and Pappas, George J. and Parrilo, Pablo A. and Recht, Benjamin and Tomlin, Claire J. and Zeilinger, Melanie N.}, ee = {http://proceedings.mlr.press/v144/amos21a.html}, interhash = {e11c16d9e6df12fe80a6f348eaa2a02c}, intrahash = {347118ec4d9779b06a76823f116dd6c5}, keywords = {dblp}, pages = {6-20}, publisher = {PMLR}, series = {Proceedings of Machine Learning Research}, timestamp = {2024-04-10T01:28:16.000+0200}, title = {On the model-based stochastic value gradient for continuous reinforcement learning.}, url = {http://dblp.uni-trier.de/db/conf/l4dc/l4dc2021.html#AmosSYW21}, volume = 144, year = 2021 }