MCPcopy Create free account
hub / github.com/rlcode/reinforcement-learning / RNDTarget

Class RNDTarget

4-atari-hard/1-ppo-rnd.py:100–107  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

98
99
100class RNDTarget(nn.Module):
101 def __init__(self):
102 super().__init__()
103 self.conv = _rnd_conv()
104 self.fc = nn.Linear(64 * 7 * 7, 512)
105
106 def forward(self, x):
107 return self.fc(self.conv(x))
108
109
110class RNDPredictor(nn.Module):

Callers 1

1-ppo-rnd.pyFile · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected