While working on PULSE, I found out that you CAN train a single MLP to reach very very high imitation success rate on AMASS with the right training procedure.
Basically, no MCP/MOE is needed as long as you train it for long enough...
3
1
17
Replies
The PNN stuff is still very useful for failure state recovery, which degrades the imitation result if not handled properly.
Code is out for training a single MLP model just for the imitation task (no recovery), and I am training a model I can release:
0
0
2
@rlfromlux
Haha well if you don't care about getting to 99.99%, training it for like 1~2 days will get you far
0
0
1
