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/configs/types.py

@@ -23,6 +23,7 @@ class FeatureType(str, Enum):
     VISUAL = "VISUAL"
     ENV = "ENV"
     ACTION = "ACTION"
+    REWARD = "REWARD"
 
 
 class NormalizationMode(str, Enum):