Adds new extensions to `pyproject.toml` (#1988)

# Description

Previously, the `pyproject.toml` was not including the newly added
`isaaclab_rl` and `isaaclab_mimic` extensions. This affected the import
ordering. This MR adds all of them under known extras.

## Type of change

- Bug fix (non-breaking change which fixes an issue)

## Checklist

- [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with
`./isaaclab.sh --format`
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have updated the changelog and the corresponding version in the
extension's `config/extension.toml` file
- [x] I have added my name to the `CONTRIBUTORS.md` or my name already
exists there

pyproject.toml

@@ -15,6 +15,7 @@ sections = [
     "ASSETS_FIRSTPARTY",
     "FIRSTPARTY",
     "EXTRA_FIRSTPARTY",
+    "TASK_FIRSTPARTY",
     "LOCALFOLDER",
 ]
 
@@ -55,8 +56,10 @@ known_third_party = [
 known_first_party = "isaaclab"
 known_assets_firstparty = "isaaclab_assets"
 known_extra_firstparty = [
-    "isaaclab_tasks"
+    "isaaclab_rl",
+    "isaaclab_mimic",
 ]
+known_task_firstparty = "isaaclab_tasks"
 # Imports from the local folder
 known_local_folder = "config"
 

scripts/benchmarks/benchmark_rlgames.py

@@ -69,7 +69,6 @@ import random
 import torch
 from datetime import datetime
 
-from isaaclab_rl.rl_games import RlGamesGpuEnv, RlGamesVecEnvWrapper
 from rl_games.common import env_configurations, vecenv
 from rl_games.common.algo_observer import IsaacAlgoObserver
 from rl_games.torch_runner import Runner
@@ -78,6 +77,8 @@ from isaaclab.envs import DirectMARLEnvCfg, DirectRLEnvCfg, ManagerBasedRLEnvCfg
 from isaaclab.utils.dict import print_dict
 from isaaclab.utils.io import dump_pickle, dump_yaml
 
+from isaaclab_rl.rl_games import RlGamesGpuEnv, RlGamesVecEnvWrapper
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils.hydra import hydra_task_config
 

scripts/benchmarks/benchmark_rsl_rl.py

@@ -68,13 +68,14 @@ import numpy as np
 import torch
 from datetime import datetime
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlVecEnvWrapper
 from rsl_rl.runners import OnPolicyRunner
 
 from isaaclab.envs import DirectMARLEnvCfg, DirectRLEnvCfg, ManagerBasedRLEnvCfg
 from isaaclab.utils.dict import print_dict
 from isaaclab.utils.io import dump_pickle, dump_yaml
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlVecEnvWrapper
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils import get_checkpoint_path
 from isaaclab_tasks.utils.hydra import hydra_task_config

scripts/imitation_learning/isaaclab_mimic/consolidated_demo.py

@@ -80,10 +80,6 @@ import random
 import time
 import torch
 
-import isaaclab_mimic.envs  # noqa: F401
-from isaaclab_mimic.datagen.data_generator import DataGenerator
-from isaaclab_mimic.datagen.datagen_info_pool import DataGenInfoPool
-
 from isaaclab.devices import Se3Keyboard, Se3SpaceMouse
 from isaaclab.envs import ManagerBasedRLMimicEnv
 from isaaclab.envs.mdp.recorders.recorders_cfg import ActionStateRecorderManagerCfg
@@ -91,6 +87,10 @@ from isaaclab.managers import DatasetExportMode, RecorderTerm, RecorderTermCfg
 from isaaclab.utils import configclass
 from isaaclab.utils.datasets import HDF5DatasetFileHandler
 
+import isaaclab_mimic.envs  # noqa: F401
+from isaaclab_mimic.datagen.data_generator import DataGenerator
+from isaaclab_mimic.datagen.datagen_info_pool import DataGenInfoPool
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils.parse_cfg import parse_env_cfg
 

scripts/imitation_learning/isaaclab_mimic/generate_dataset.py

@@ -51,14 +51,14 @@ import os
 import random
 import torch
 
-import isaaclab_mimic.envs  # noqa: F401
-from isaaclab_mimic.datagen.data_generator import DataGenerator
-from isaaclab_mimic.datagen.datagen_info_pool import DataGenInfoPool
-
 from isaaclab.envs.mdp.recorders.recorders_cfg import ActionStateRecorderManagerCfg
 from isaaclab.managers import DatasetExportMode
 from isaaclab.utils.datasets import HDF5DatasetFileHandler
 
+import isaaclab_mimic.envs  # noqa: F401
+from isaaclab_mimic.datagen.data_generator import DataGenerator
+from isaaclab_mimic.datagen.datagen_info_pool import DataGenInfoPool
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils.parse_cfg import parse_env_cfg
 

scripts/reinforcement_learning/rl_games/play.py

@@ -53,7 +53,6 @@ import os
 import time
 import torch
 
-from isaaclab_rl.rl_games import RlGamesGpuEnv, RlGamesVecEnvWrapper
 from rl_games.common import env_configurations, vecenv
 from rl_games.common.player import BasePlayer
 from rl_games.torch_runner import Runner
@@ -63,6 +62,8 @@ from isaaclab.utils.assets import retrieve_file_path
 from isaaclab.utils.dict import print_dict
 from isaaclab.utils.pretrained_checkpoint import get_published_pretrained_checkpoint
 
+from isaaclab_rl.rl_games import RlGamesGpuEnv, RlGamesVecEnvWrapper
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils import get_checkpoint_path, load_cfg_from_registry, parse_env_cfg
 

scripts/reinforcement_learning/rl_games/train.py

@@ -50,7 +50,6 @@ import os
 import random
 from datetime import datetime
 
-from isaaclab_rl.rl_games import RlGamesGpuEnv, RlGamesVecEnvWrapper
 from rl_games.common import env_configurations, vecenv
 from rl_games.common.algo_observer import IsaacAlgoObserver
 from rl_games.torch_runner import Runner
@@ -66,6 +65,8 @@ from isaaclab.utils.assets import retrieve_file_path
 from isaaclab.utils.dict import print_dict
 from isaaclab.utils.io import dump_pickle, dump_yaml
 
+from isaaclab_rl.rl_games import RlGamesGpuEnv, RlGamesVecEnvWrapper
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils.hydra import hydra_task_config
 

scripts/reinforcement_learning/rsl_rl/play.py

@@ -49,7 +49,6 @@ import os
 import time
 import torch
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlVecEnvWrapper, export_policy_as_jit, export_policy_as_onnx
 from rsl_rl.runners import OnPolicyRunner
 
 from isaaclab.envs import DirectMARLEnv, multi_agent_to_single_agent
@@ -57,6 +56,8 @@ from isaaclab.utils.assets import retrieve_file_path
 from isaaclab.utils.dict import print_dict
 from isaaclab.utils.pretrained_checkpoint import get_published_pretrained_checkpoint
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlVecEnvWrapper, export_policy_as_jit, export_policy_as_onnx
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils import get_checkpoint_path, parse_env_cfg
 

scripts/reinforcement_learning/rsl_rl/train.py

@@ -49,7 +49,6 @@ import os
 import torch
 from datetime import datetime
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlVecEnvWrapper
 from rsl_rl.runners import OnPolicyRunner
 
 from isaaclab.envs import (
@@ -62,6 +61,8 @@ from isaaclab.envs import (
 from isaaclab.utils.dict import print_dict
 from isaaclab.utils.io import dump_pickle, dump_yaml
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlVecEnvWrapper
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils import get_checkpoint_path
 from isaaclab_tasks.utils.hydra import hydra_task_config

scripts/reinforcement_learning/sb3/play.py

@@ -52,7 +52,6 @@ import os
 import time
 import torch
 
-from isaaclab_rl.sb3 import Sb3VecEnvWrapper, process_sb3_cfg
 from stable_baselines3 import PPO
 from stable_baselines3.common.vec_env import VecNormalize
 
@@ -60,6 +59,8 @@ from isaaclab.envs import DirectMARLEnv, multi_agent_to_single_agent
 from isaaclab.utils.dict import print_dict
 from isaaclab.utils.pretrained_checkpoint import get_published_pretrained_checkpoint
 
+from isaaclab_rl.sb3 import Sb3VecEnvWrapper, process_sb3_cfg
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils.parse_cfg import get_checkpoint_path, load_cfg_from_registry, parse_env_cfg
 

scripts/reinforcement_learning/sb3/train.py

@@ -49,7 +49,6 @@ import os
 import random
 from datetime import datetime
 
-from isaaclab_rl.sb3 import Sb3VecEnvWrapper, process_sb3_cfg
 from stable_baselines3 import PPO
 from stable_baselines3.common.callbacks import CheckpointCallback
 from stable_baselines3.common.logger import configure
@@ -65,6 +64,8 @@ from isaaclab.envs import (
 from isaaclab.utils.dict import print_dict
 from isaaclab.utils.io import dump_pickle, dump_yaml
 
+from isaaclab_rl.sb3 import Sb3VecEnvWrapper, process_sb3_cfg
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils.hydra import hydra_task_config
 

scripts/reinforcement_learning/skrl/play.py

@@ -82,12 +82,12 @@ if args_cli.ml_framework.startswith("torch"):
 elif args_cli.ml_framework.startswith("jax"):
     from skrl.utils.runner.jax import Runner
 
-from isaaclab_rl.skrl import SkrlVecEnvWrapper
-
 from isaaclab.envs import DirectMARLEnv, multi_agent_to_single_agent
 from isaaclab.utils.dict import print_dict
 from isaaclab.utils.pretrained_checkpoint import get_published_pretrained_checkpoint
 
+from isaaclab_rl.skrl import SkrlVecEnvWrapper
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils import get_checkpoint_path, load_cfg_from_registry, parse_env_cfg
 

scripts/reinforcement_learning/skrl/train.py

@@ -84,8 +84,6 @@ if args_cli.ml_framework.startswith("torch"):
 elif args_cli.ml_framework.startswith("jax"):
     from skrl.utils.runner.jax import Runner
 
-from isaaclab_rl.skrl import SkrlVecEnvWrapper
-
 from isaaclab.envs import (
     DirectMARLEnv,
     DirectMARLEnvCfg,
@@ -97,6 +95,8 @@ from isaaclab.utils.assets import retrieve_file_path
 from isaaclab.utils.dict import print_dict
 from isaaclab.utils.io import dump_pickle, dump_yaml
 
+from isaaclab_rl.skrl import SkrlVecEnvWrapper
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils.hydra import hydra_task_config
 

source/isaaclab_mimic/isaaclab_mimic/datagen/data_generator.py

@@ -10,13 +10,13 @@ import asyncio
 import numpy as np
 import torch
 
+import isaaclab.utils.math as PoseUtils
+from isaaclab.envs.mimic_env_cfg import MimicEnvCfg
+
 from isaaclab_mimic.datagen.datagen_info import DatagenInfo
 from isaaclab_mimic.datagen.selection_strategy import make_selection_strategy
 from isaaclab_mimic.datagen.waypoint import WaypointSequence, WaypointTrajectory
 
-import isaaclab.utils.math as PoseUtils
-from isaaclab.envs.mimic_env_cfg import MimicEnvCfg
-
 from .datagen_info_pool import DataGenInfoPool
 
 

source/isaaclab_mimic/isaaclab_mimic/datagen/datagen_info_pool.py

@@ -5,11 +5,11 @@
 
 import asyncio
 
-from isaaclab_mimic.datagen.datagen_info import DatagenInfo
-
 import isaaclab.utils.math as PoseUtils
 from isaaclab.utils.datasets import EpisodeData, HDF5DatasetFileHandler
 
+from isaaclab_mimic.datagen.datagen_info import DatagenInfo
+
 
 class DataGenInfoPool:
     """

source/isaaclab_mimic/test/test_selection_strategy.py

@@ -12,6 +12,8 @@ import numpy as np
 import torch
 import unittest
 
+import isaaclab.utils.math as PoseUtils
+
 from isaaclab_mimic.datagen.datagen_info import DatagenInfo
 
 # Importing the necessary classes for the testing
@@ -20,8 +22,6 @@ from isaaclab_mimic.datagen.selection_strategy import (
     NearestNeighborRobotDistanceStrategy,
 )
 
-import isaaclab.utils.math as PoseUtils
-
 # Number of iterations to run the batched tests
 NUM_ITERS = 1000
 

source/isaaclab_rl/test/test_rl_games_wrapper.py

@@ -20,10 +20,11 @@ import unittest
 
 import carb
 import omni.usd
-from isaaclab_rl.rl_games import RlGamesVecEnvWrapper
 
 from isaaclab.envs import DirectMARLEnv, multi_agent_to_single_agent
 
+from isaaclab_rl.rl_games import RlGamesVecEnvWrapper
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils.parse_cfg import parse_env_cfg
 

source/isaaclab_rl/test/test_rsl_rl_wrapper.py

@@ -20,10 +20,11 @@ import unittest
 
 import carb
 import omni.usd
-from isaaclab_rl.rsl_rl import RslRlVecEnvWrapper
 
 from isaaclab.envs import DirectMARLEnv, multi_agent_to_single_agent
 
+from isaaclab_rl.rsl_rl import RslRlVecEnvWrapper
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils.parse_cfg import parse_env_cfg
 

source/isaaclab_rl/test/test_sb3_wrapper.py

@@ -21,10 +21,11 @@ import unittest
 
 import carb
 import omni.usd
-from isaaclab_rl.sb3 import Sb3VecEnvWrapper
 
 from isaaclab.envs import DirectMARLEnv, multi_agent_to_single_agent
 
+from isaaclab_rl.sb3 import Sb3VecEnvWrapper
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils.parse_cfg import parse_env_cfg
 

source/isaaclab_rl/test/test_skrl_wrapper.py

@@ -20,10 +20,11 @@ import unittest
 
 import carb
 import omni.usd
-from isaaclab_rl.skrl import SkrlVecEnvWrapper
 
 from isaaclab.envs import DirectMARLEnv, multi_agent_to_single_agent
 
+from isaaclab_rl.skrl import SkrlVecEnvWrapper
+
 import isaaclab_tasks  # noqa: F401
 from isaaclab_tasks.utils.parse_cfg import parse_env_cfg
 

source/isaaclab_tasks/isaaclab_tasks/direct/allegro_hand/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class AllegroHandPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/direct/ant/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class AntPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/direct/anymal_c/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class AnymalCFlatPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/direct/cartpole/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class CartpolePPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/direct/franka_cabinet/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class FrankaCabinetPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/direct/humanoid/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class HumanoidPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/direct/quadcopter/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class QuadcopterPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/direct/shadow_hand/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class ShadowHandPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/classic/ant/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class AntPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/classic/cartpole/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class CartpolePPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/classic/humanoid/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class HumanoidPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/locomotion/velocity/config/a1/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class UnitreeA1RoughPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/locomotion/velocity/config/anymal_b/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class AnymalBRoughPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/locomotion/velocity/config/anymal_c/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class AnymalCRoughPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/locomotion/velocity/config/anymal_d/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class AnymalDRoughPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/locomotion/velocity/config/cassie/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class CassieRoughPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/locomotion/velocity/config/g1/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class G1RoughPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/locomotion/velocity/config/go1/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class UnitreeGo1RoughPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/locomotion/velocity/config/go2/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class UnitreeGo2RoughPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/locomotion/velocity/config/h1/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class H1RoughPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/locomotion/velocity/config/spot/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class SpotFlatPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/cabinet/config/franka/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class CabinetPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/inhand/config/allegro_hand/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class AllegroCubePPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/lift/config/franka/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class LiftCubePPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/reach/config/franka/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class FrankaReachPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/reach/config/ur_10/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class UR10ReachPPORunnerCfg(RslRlOnPolicyRunnerCfg):

source/isaaclab_tasks/isaaclab_tasks/manager_based/navigation/config/anymal_c/agents/rsl_rl_ppo_cfg.py

@@ -3,10 +3,10 @@
 #
 # SPDX-License-Identifier: BSD-3-Clause
 
-from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
-
 from isaaclab.utils import configclass
 
+from isaaclab_rl.rsl_rl import RslRlOnPolicyRunnerCfg, RslRlPpoActorCriticCfg, RslRlPpoAlgorithmCfg
+
 
 @configclass
 class NavigationEnvPPORunnerCfg(RslRlOnPolicyRunnerCfg):