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

Method features

4-atari-hard/3-robustify.py:94–96  ·  view source on GitHub ↗
(self, obs)

Source from the content-addressed store, hash-verified

92 self.gru_dim = gru_dim
93
94 def features(self, obs):
95 h = self.ln(torch.relu(self.fc(self.conv(obs / 255.0))))
96 return h
97
98 def step(self, obs, hx, inc_entropy=None):
99 """One timestep for acting. obs (B,4,105,80), hx (B,gru). Returns

Callers 2

stepMethod · 0.95
unrollMethod · 0.95

Calls

no outgoing calls

Tested by

no test coverage detected