MMOneSphere: BC_PCL_PNet2_avg_flow2ee
Try the backprop-through-average. Compare this with `BC_PCL_PNet2_avg_ee` the only difference is whether we use `flow2ee` (here) or the raw ee, which reflects the effect of collisions. Since we use flow, I am guessing performance should be a bit worse. (Edit: maybe not! It looks good here!) Remember, here we have 3D flow per point, and since demonstrator just did translation, that turns into our "EE position change" as averaging all the flow means we get the same thing.
Created on April 20|Last edited on April 25
Comment
(0.6276 + 0.5427 + 0.4535) / 3 = 0.5412
Train/Eval MSEs, Episode Success/Reward
Run set
3
Example GIFs
Huh now we can get sideways movement even with "flow" as input.
First seed after 250 epochs:
Second seed after 250 epochs:
Third seed after 250 epochs:
Add a comment