MMOneSphere: BC_PCL_PNet2_flow
Segmentation version of PN++, regressing onto flow. Challenges: (a) MSE is per-point, (b) flow loses collision info. So this is not expected to work well, and is mainly a baseline. (Update: as expected, pretty bad performance)
Created on April 21|Last edited on April 25
Comment
(0.1342 + 0.04514 + 0.03635) / 3 = 0.0718
Train/Eval MSEs, Episode Success/Reward
Run set
3
Example GIFs
Some pretty bad performance here, suggesting we should NOT just predict tool flow and regress pointwise on these.
The first seed after 250 epochs. There is a tiny bit of sideways movement.
Second seed after 250 epochs:
Third seed after 250 epochs:
Add a comment