[Port HIL_SERL] Final fixes for the Reward Classifier (#598)

2025-01-06 17:34:00 +07:00
parent 35de91ef2b
commit c5bca1cf0f
11 changed files with 59 additions and 19 deletions
--- a/lerobot/common/policies/sac/modeling_sac.py
+++ b/lerobot/common/policies/sac/modeling_sac.py
@@ -333,7 +333,6 @@ class Critic(nn.Module):
        value = self.output_layer(x)
        return value.squeeze(-1)

-
 class Policy(nn.Module):
    def __init__(
        self,