huangfu/InteractionImitation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix discriminator reward

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

8
scratch/etienne/intersimple/gail_options_image.py
View File

@@ -135,9 +135,11 @@ class HLOptions(OptionsEnv):
self.steps = 0
def _after_step(self):
self.r += self.discount**self.steps * self.discriminator.discrim_net.discriminator(
torch.tensor(self.s).unsqueeze(0).to(self.discriminator.discrim_net.device()),
torch.tensor([[self.a]]).to(self.discriminator.discrim_net.device()),
self.r += self.discount**self.steps * self.discriminator.discrim_net.reward_train(
state=torch.tensor(self.s).unsqueeze(0).to(self.discriminator.discrim_net.device()),
action=torch.tensor([[self.a]]).to(self.discriminator.discrim_net.device()),
next_state=torch.tensor(self.s).unsqueeze(0).to(self.discriminator.discrim_net.device()), # unused
done=torch.tensor(self.done).unsqueeze(0).to(self.discriminator.discrim_net.device()), # unused
)
self.steps += 1