Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[BugFix] Fix LSTM in GAE with vmap #2376

Merged
merged 1 commit into from
Aug 7, 2024
Merged

[BugFix] Fix LSTM in GAE with vmap #2376

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
[BugFix] Fix LSTM in GAE with vmap
  • Loading branch information
@vmoens
vmoens committed Aug 7, 2024
commit 1152c07fa1cf4256a8a82b73f5c9085ae6518937
2 changes: 1 addition & 1 deletion torchrl/modules/tensordict_module/rnn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -687,7 +687,7 @@ def forward(self, tensordict: TensorDictBase):
# packed sequences do not help to get the accurate last hidden values
# if splits is not None:
# value = torch.nn.utils.rnn.pack_padded_sequence(value, splits, batch_first=True)
if is_init.any() and hidden0 is not None:
if hidden0 is not None:
is_init_expand = expand_as_right(is_init, hidden0)
hidden0 = torch.where(is_init_expand, 0, hidden0)
hidden1 = torch.where(is_init_expand, 0, hidden1)
Expand Down
Loading