tangger/lerobot
1
0
Fork 1
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Fixes for the reward classifier

Browse Source
This commit is contained in:
Michel Aractingi
2025-04-15 18:12:21 +02:00
committed by Michel Aractingi
parent 54c3c6d684
commit 3b24ad3c84
4 changed files with 64 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
lerobot/common/envs/configs.py
View File

@@ -225,12 +225,7 @@ class HILSerlRobotEnvConfig(EnvConfig):
device: str = "cuda"
push_to_hub: bool = True
pretrained_policy_name_or_path: Optional[str] = None
reward_classifier: dict[str, str | None] = field(
default_factory=lambda: {
"pretrained_path": None,
"config_path": None,
}
)
reward_classifier_pretrained_path: Optional[str] = None
def gym_kwargs(self) -> dict:
return {}
@@ -271,12 +266,7 @@ class ManiskillEnvConfig(EnvConfig):
"observation.state": OBS_ROBOT,
}
)
reward_classifier: dict[str, str | None] = field(
default_factory=lambda: {
"pretrained_path": None,
"config_path": None,
}
)
reward_classifier_pretrained_path: Optional[str] = None
@property
def gym_kwargs(self) -> dict: