MMMultiSphere (v02): BC_PCL_PNet2_flow2ee
Let's see if flow2ee is a bit worse compared to just ee. This is with the classification PN++. It would be good to get more verification that the action magnitudes could cause a difference in performance (this seems reasonable to me).
Created on April 23|Last edited on April 25
Comment
(0.05742 + 0.03389 + 0.02297) / 3 = 0.0380
Train/Eval MSEs, Episode Success/Reward
Run set
3
Example GIFs:
First seed after 250:
Second seed after 250:
Third seed after 250:
Add a comment