Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/rlcode/reinforcement-learning
/ _ortho
Function
_ortho
3-atari/2-ppo.py:34–37 ·
view source on GitHub ↗
(layer, gain)
Source
from the content-addressed store, hash-verified
32
33
34
def
_ortho(layer, gain):
35
nn.init.orthogonal_(layer.weight, gain)
36
nn.init.zeros_(layer.bias)
37
return
layer
38
39
40
# Nature CNN shared trunk + policy and value heads.
Callers
1
__init__
Method · 0.70
Calls
no outgoing calls
Tested by
no test coverage detected