Skip to content

fix(reward_classifier): remove leftover normalization calls from predict_reward #2355

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

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix(reward_classifier): remove leftover normalization calls from predict_reward #2355

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3b6a28e
fix(reward_classifier): remove leftover normalization calls from pred…
TheWisp Nov 1, 2025
094ee43
Merge branch 'main' into fix/reward-classifier-normalization
TheWisp Nov 25, 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
4 changes: 0 additions & 4 deletions src/lerobot/policies/sac/reward_model/modeling_classifier.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -268,10 +268,6 @@ def forward(self, batch: dict[str, Tensor]) -> tuple[Tensor, dict[str, Tensor]]:

def predict_reward(self, batch, threshold=0.5):
"""Eval method. Returns predicted reward with the decision threshold as argument."""
# Check for both OBS_IMAGE and OBS_IMAGES prefixes
batch = self.normalize_inputs(batch)
batch = self.normalize_targets(batch)

# Extract images from batch dict
images = [batch[key] for key in self.config.input_features if key.startswith(OBS_IMAGE)]

Expand Down