search

PufferAI / PufferLib

Simplifying reinforcement learning for complex game environments
https://pufferai.github.io/
MIT License
1.04k stars 41 forks source link

Enabled 0 layer recurrent wrapper for testing #72

Closed kywch closed 6 months ago

kywch commented 6 months ago

RecurrentWrapper class can accept num_layer = 0, so the model scaling experiment can run from 0 to N layers.