|
|
|
|
|
|
by dadoomer
9 hours ago
|
|
|
I'm also interested in how they figured out how to get the CMA-ES baseline to be this fast (less than 35 samples in Figure 5). Maybe they are warm-starting CMA-ES with a pre-trained controller (although at a glance it doesn't seem they do). Haven't read the paper yet though. |
|
|