[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

src/lerobot/scripts/rl/actor.py

@@ -62,8 +62,14 @@ from lerobot.configs import parser
 from lerobot.configs.train import TrainRLServerPipelineConfig
 from lerobot.policies.factory import make_policy
 from lerobot.policies.sac.modeling_sac import SACPolicy
+from lerobot.processor.pipeline import TransitionKey
 from lerobot.robots import so100_follower  # noqa: F401
-from lerobot.scripts.rl.gym_manipulator import make_robot_env
+from lerobot.scripts.rl.gym_manipulator import (
+    create_transition,
+    make_processors,
+    make_robot_env,
+    step_env_and_process_transition,
+)
 from lerobot.teleoperators import gamepad, so101_leader  # noqa: F401
 from lerobot.transport import services_pb2, services_pb2_grpc
 from lerobot.transport.utils import (
@@ -83,13 +89,6 @@ from lerobot.utils.transition import (
     move_state_dict_to_device,
     move_transition_to_device,
 )
-
-from lerobot.processor.pipeline import EnvTransition, TransitionKey
-from lerobot.scripts.rl.gym_manipulator import (
-    create_transition,
-    make_processors,
-    step_env_and_process_transition,
-)
 from lerobot.utils.utils import (
     TimerManager,
     get_safe_torch_device,
@@ -311,13 +310,13 @@ def act_with_policy(
             env_processor=env_processor,
             action_processor=action_processor,
         )
-        
+
         # Extract values from processed transition
         reward = new_transition[TransitionKey.REWARD]
         done = new_transition.get(TransitionKey.DONE, False)
         truncated = new_transition.get(TransitionKey.TRUNCATED, False)
         processed_action = new_transition[TransitionKey.ACTION]
-        
+
         sum_reward_episode += float(reward)
         episode_total_steps += 1
 
@@ -381,7 +380,7 @@ def act_with_policy(
             episode_intervention = False
             episode_intervention_steps = 0
             episode_total_steps = 0
-            
+
             # Reset environment and processors
             obs, info = online_env.reset()
             complementary_data = {"raw_joint_positions": info.pop("raw_joint_positions")}

src/lerobot/scripts/rl/gym_manipulator.py

@@ -783,11 +783,11 @@ def make_robot_env(cfg: EnvConfig) -> tuple[gym.Env, Any]:
 def make_processors(env, cfg):
     """
     Factory function to create environment and action processors.
-    
+
     Args:
         env: The robot environment
         cfg: Configuration object containing processor parameters
-    
+
     Returns:
         tuple: (env_processor, action_processor)
     """
@@ -797,13 +797,11 @@ def make_processors(env, cfg):
         JointVelocityProcessor(dt=1.0 / cfg.fps),
         MotorCurrentProcessor(env=env),
         ImageCropResizeProcessor(
-            crop_params_dict=cfg.processor.crop_params_dict, 
+            crop_params_dict=cfg.processor.crop_params_dict, resize_size=cfg.processor.resize_size
-            resize_size=cfg.processor.resize_size
         ),
         TimeLimitProcessor(max_episode_steps=int(cfg.processor.control_time_s * cfg.fps)),
         GripperPenaltyProcessor(
-            penalty=cfg.processor.gripper_penalty, 
+            penalty=cfg.processor.gripper_penalty, max_gripper_pos=cfg.processor.max_gripper_pos
-            max_gripper_pos=cfg.processor.max_gripper_pos
         ),
         DeviceProcessor(device=cfg.device),
     ]
@@ -823,21 +821,21 @@ def make_processors(env, cfg):
         ),
     ]
     action_processor = RobotProcessor(steps=action_pipeline_steps)
-    
+
     return env_processor, action_processor
 
 
 def step_env_and_process_transition(
-    env, 
+    env,
-    transition, 
+    transition,
-    action, 
+    action,
-    teleop_device, 
+    teleop_device,
-    env_processor, 
+    env_processor,
-    action_processor, 
+    action_processor,
 ):
     """
     Execute one step with processors handling intervention and observation processing.
-    
+
     Args:
         env: The robot environment
         transition: Current transition state
@@ -845,7 +843,7 @@ def step_env_and_process_transition(
         teleop_device: Teleoperator device for getting intervention signals
         env_processor: Environment processor for observations
         action_processor: Action processor for handling interventions
-    
+
     Returns:
         tuple: (new_transition, terminate_episode)
     """
@@ -893,7 +891,7 @@ def step_env_and_process_transition(
         complementary_data=complementary_data,
     )
     new_transition = env_processor(new_transition)
-    
+
     return new_transition, terminate_episode