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

Method forward

2-cartpole/3-ppo.py:81–83  ·  view source on GitHub ↗
(self, x)

Source from the content-addressed store, hash-verified

79 self.value = _ortho(nn.Linear(64, 1), gain=1.0)
80
81 def forward(self, x):
82 h = self.shared(x)
83 return self.policy(h), self.value(h).squeeze(-1)
84
85
86# GAE-lambda: backward recursion over the collected rollout.

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected