Skip to main content

MMMultiSphere (v02): BC_PCL_PNet2_avg_flow2ee

To compare with: (a) PN++ with classification flow2ee, so to see effect of the two architectures of PN++, (b) PN++ with average layer but with ee, to see the effect (deterioration?) of using flow instead of ee with the loss of collision information.
Created on April 23|Last edited on April 25
(0.3669+ 0.09318 + 0.05749) / 3 = 0.1725

Train/Eval MSEs, Episode Success/Reward


50100150200Step0.010.020.030.040.05
050100150200Step0.060.080.10.12
050100150200Step00.20.40.60.8
Run set
3


Example GIFs:

First seed after 250 epochs:

Second seed after 250 epochs (this is the one that did reasonably well).

Third seed after 250 epochs: