Samuel K. AinsworthKendall LowreyJohn ThickstunZaïd HarchaouiSiddhartha S. SrinivasaFaster Policy Learning with Continuous-Time Gradients.1054-10672021L4DChttp://proceedings.mlr.press/v144/ainsworth21a.htmlconf/l4dc/2021db/conf/l4dc/l4dc2021.html#AinsworthLTHS21