Change HILSerlRobotEnvConfig to inherit from EnvConfig

Added support for hil_serl classifier to be trained with train.py
run classifier training by python lerobot/scripts/train.py --policy.type=hilserl_classifier
fixes in find_joint_limits, control_robot, end_effector_control_utils

lerobot/common/policies/factory.py

@@ -28,6 +28,7 @@ from lerobot.common.policies.pi0.configuration_pi0 import PI0Config
 from lerobot.common.policies.pretrained import PreTrainedPolicy
 from lerobot.common.policies.tdmpc.configuration_tdmpc import TDMPCConfig
 from lerobot.common.policies.vqbet.configuration_vqbet import VQBeTConfig
+from lerobot.common.policies.hilserl.classifier.configuration_classifier import ClassifierConfig
 from lerobot.configs.policies import PreTrainedConfig
 from lerobot.configs.types import FeatureType
 
@@ -58,6 +59,10 @@ def get_policy_class(name: str) -> PreTrainedPolicy:
         from lerobot.common.policies.sac.modeling_sac import SACPolicy
 
         return SACPolicy
+    elif name == "hilserl_classifier":
+        from lerobot.common.policies.hilserl.classifier.modeling_classifier import Classifier
+
+        return Classifier
     else:
         raise NotImplementedError(f"Policy with name {name} is not implemented.")
 
@@ -73,6 +78,8 @@ def make_policy_config(policy_type: str, **kwargs) -> PreTrainedConfig:
         return VQBeTConfig(**kwargs)
     elif policy_type == "pi0":
         return PI0Config(**kwargs)
+    elif policy_type == "hilserl_classifier":
+        return ClassifierConfig(**kwargs)
     else:
         raise ValueError(f"Policy type '{policy_type}' is not available.")