Fix discriminator reward

Had wrong sign.
This commit is contained in:
ebuehrle
2021-09-15 07:15:43 +02:00
parent 183657dc36
commit 4928458e08
2 changed files with 9 additions and 5 deletions

View File

@@ -36,7 +36,8 @@ class CnnDiscriminator(torch.nn.Module):
def forward(self, state, action):
sa = self._concatenate(state, action)
return self.cnn(sa).squeeze()
assert sa.ndim == 4
return self.cnn(sa).squeeze(1)
class MlpDiscriminator(torch.nn.Module):
"""MLP similar to stable_baselines3.common.policies.ActorCriticPolicy."""
@@ -55,4 +56,5 @@ class MlpDiscriminator(torch.nn.Module):
def forward(self, state, action):
flat = self.flatten(state)
sa = torch.cat((action, flat), -1)
return self.mlp(sa).squeeze()
assert sa.ndim == 2
return self.mlp(sa).squeeze(1)