(self, x)
| 39 | self.rewards = [] |
| 40 | |
| 41 | def forward(self, x): |
| 42 | x = self.affine1(x) |
| 43 | x = self.dropout(x) |
| 44 | x = F.relu(x) |
| 45 | action_scores = self.affine2(x) |
| 46 | return F.softmax(action_scores, dim=1) |
| 47 | |
| 48 | |
| 49 | policy = Policy() |
nothing calls this directly
no outgoing calls
no test coverage detected