Skip to content

Fix BasicEntropyLossFn #77

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

Merged
yanxi-chen merged 3 commits into from
Jun 11, 2025
Merged

Fix BasicEntropyLossFn #77

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7e8c944
1. Init BasicEntropyLossFn default_args entropy_coef using zero, othe…
Jun 11, 2025
b5d3e09
1. Init BasicEntropyLossFn default_args entropy_coef using zero, othe…
Jun 11, 2025
cece606
1. Reformat
Jun 11, 2025
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
2 changes: 1 addition & 1 deletion docs/sphinx_doc/source/tutorial/trinity_programming_guide.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -299,7 +299,7 @@ pip install -e .[dev]
# pip install -e .\[dev\]

# Run code style checks
pre-commit --all-files
pre-commit run --all-files

# Commit the code after all checks pass
git commit -am "create example workflow"
Expand Down
10 changes: 1 addition & 9 deletions trinity/algorithm/entropy_loss_fn/entropy_loss_fn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,12 +32,12 @@ def __call__(
"""

@classmethod
@abstractmethod
def default_args(cls) -> Dict:
"""
Returns:
`Dict`: The default arguments for the entropy loss function.
"""
return {"entropy_coef": 0.0}


@ENTROPY_LOSS_FN.register_module("basic")
Expand All @@ -58,10 +58,6 @@ def __call__(
entropy_loss = masked_mean(entropy, action_mask)
return entropy_loss * self.entropy_coef, {"entropy_loss": entropy_loss.detach().item()}

@classmethod
def default_args(cls) -> Dict:
return {"entropy_coef": 0.0}


@ENTROPY_LOSS_FN.register_module("none")
class DummyEntropyLossFn(EntropyLossFn):
Expand All @@ -79,7 +75,3 @@ def __call__(
**kwargs,
) -> Tuple[torch.Tensor, Dict]:
return torch.tensor(0.0), {}

@classmethod
def default_args(cls) -> Dict:
return {}