Weight Agnostic Neural Networks
Luo Yi
Dec. 12, 2019
Pros & Cons of WANNs
Experiments with Reinforcement Learning Tasks
- Swing Up
- Biped
- CarRacing
Performance Along with Fixed Topology
Weights\score\Swing Up:WANN,Fixed Topology
Random,57,21
Random Shared,515,7
Tuned Shared,723,8
Tuned,932,918
Weights\score\Biped:WANN,Fixed Topology
Random,-46,-129
Random Shared,51,-107
Tuned Shared,261,-35
Tuned,332,347
Weights\score\CarRacing:WANN,Fixed Topology
Random,-69,-82
Random Shared,375,-85
Tuned Shared,608,-37
Tuned,893,906
Why?
WANNs' weights are trained to be so.
- Without training, it can do.
- With little training, it's near optimal.
Parameters and HyperParameters
But it is unfair.
WANNs' architectures are shrunk to be so.
Can WANN beat NAS? I wonder.
Page Not Found
Try to search through the entire repo.