[Exp] Cherry-pick direct warp envs from dev/newton

CONTRIBUTORS.md

@@ -96,6 +96,7 @@ Guidelines for modifications:
 * Ji Yuan Feng
 * Jia Lin Yuan
 * Jiakai Zhang
+* Jichuan Hu
 * Jinghuan Shang
 * Jingzhou Liu
 * Jinqi Wei

scripts/reinforcement_learning/rl_games/play.py

@@ -6,6 +6,7 @@
 """Script to play a checkpoint if an RL agent from RL-Games."""
 
 import argparse
+import contextlib
 import math
 import os
 import random
@@ -29,6 +30,8 @@
 from isaaclab_tasks.utils import add_launcher_args, get_checkpoint_path, launch_simulation, resolve_task_config
 
 # PLACEHOLDER: Extension template (do not remove this comment)
+with contextlib.suppress(ImportError):
+    import isaaclab_tasks_experimental  # noqa: F401
 
 # -- argparse ----------------------------------------------------------------
 parser = argparse.ArgumentParser(description="Play a checkpoint of an RL agent from RL-Games.")

scripts/reinforcement_learning/rl_games/train.py

@@ -6,6 +6,7 @@
 """Script to train RL agent with RL-Games."""
 
 import argparse
+import contextlib
 import logging
 import math
 import os
@@ -33,6 +34,8 @@
 logger = logging.getLogger(__name__)
 
 # PLACEHOLDER: Extension template (do not remove this comment)
+with contextlib.suppress(ImportError):
+    import isaaclab_tasks_experimental  # noqa: F401
 
 # -- argparse ----------------------------------------------------------------
 parser = argparse.ArgumentParser(description="Train an RL agent with RL-Games.")

scripts/reinforcement_learning/rsl_rl/play.py

@@ -6,6 +6,7 @@
 """Script to play a checkpoint if an RL agent from RSL-RL."""
 
 import argparse
+import contextlib
 import importlib.metadata as metadata
 import os
 import sys
@@ -37,6 +38,8 @@
 import cli_args  # isort: skip
 
 # PLACEHOLDER: Extension template (do not remove this comment)
+with contextlib.suppress(ImportError):
+    import isaaclab_tasks_experimental  # noqa: F401
 
 # -- argparse ----------------------------------------------------------------
 parser = argparse.ArgumentParser(description="Train an RL agent with RSL-RL.")

scripts/reinforcement_learning/rsl_rl/train.py

@@ -6,6 +6,7 @@
 """Script to train RL agent with RSL-RL."""
 
 import argparse
+import contextlib
 import importlib.metadata as metadata
 import logging
 import os
@@ -35,6 +36,8 @@
 logger = logging.getLogger(__name__)
 
 # PLACEHOLDER: Extension template (do not remove this comment)
+with contextlib.suppress(ImportError):
+    import isaaclab_tasks_experimental  # noqa: F401
 
 RSL_RL_VERSION = "3.0.1"
 

scripts/reinforcement_learning/sb3/play.py

@@ -6,6 +6,7 @@
 """Script to play a checkpoint if an RL agent from Stable-Baselines3."""
 
 import argparse
+import contextlib
 import os
 import random
 import sys
@@ -27,6 +28,8 @@
 from isaaclab_tasks.utils import add_launcher_args, get_checkpoint_path, launch_simulation, resolve_task_config
 
 # PLACEHOLDER: Extension template (do not remove this comment)
+with contextlib.suppress(ImportError):
+    import isaaclab_tasks_experimental  # noqa: F401
 
 # -- argparse ----------------------------------------------------------------
 parser = argparse.ArgumentParser(description="Play a checkpoint of an RL agent from Stable-Baselines3.")

scripts/reinforcement_learning/sb3/train.py

@@ -35,6 +35,8 @@
 logger = logging.getLogger(__name__)
 
 # PLACEHOLDER: Extension template (do not remove this comment)
+with contextlib.suppress(ImportError):
+    import isaaclab_tasks_experimental  # noqa: F401
 
 # -- argparse ----------------------------------------------------------------
 parser = argparse.ArgumentParser(description="Train an RL agent with Stable-Baselines3.")

scripts/reinforcement_learning/skrl/play.py

@@ -11,6 +11,7 @@
 """
 
 import argparse
+import contextlib
 import os
 import random
 import sys
@@ -30,6 +31,8 @@
 from isaaclab_tasks.utils import add_launcher_args, get_checkpoint_path, launch_simulation, resolve_task_config
 
 # PLACEHOLDER: Extension template (do not remove this comment)
+with contextlib.suppress(ImportError):
+    import isaaclab_tasks_experimental  # noqa: F401
 
 SKRL_VERSION = "1.4.3"
 

scripts/reinforcement_learning/skrl/train.py

@@ -11,6 +11,7 @@
 """
 
 import argparse
+import contextlib
 import logging
 import os
 import random
@@ -35,6 +36,8 @@
 logger = logging.getLogger(__name__)
 
 # PLACEHOLDER: Extension template (do not remove this comment)
+with contextlib.suppress(ImportError):
+    import isaaclab_tasks_experimental  # noqa: F401
 
 SKRL_VERSION = "1.4.3"
 

source/isaaclab_experimental/config/extension.toml

@@ -0,0 +1,21 @@
+[package]
+
+# Note: Semantic Versioning is used: https://semver.org/
+version = "0.0.1"
+
+# Description
+title = "Experimental playground for upcoming IsaacLab features"
+description="Provides early access to future features that are not yet `production-ready`."
+readme  = "docs/README.md"
+repository = "https://github.com/isaac-sim/IsaacLab"
+category = "robotics"
+keywords = ["robotics", "simulation", "experimental"]
+
+[dependencies]
+"isaaclab" = {}
+
+[core]
+reloadable = false
+
+[[python.module]]
+name = "isaaclab_experimental"

source/isaaclab_experimental/isaaclab_experimental/__init__.py

@@ -0,0 +1,20 @@
+# Copyright (c) 2022-2026, The Isaac Lab Project Developers (https://github.com/isaac-sim/IsaacLab/blob/main/CONTRIBUTORS.md).
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Package containing the core framework."""
+
+import os
+import toml
+from enum import IntEnum
+
+# Conveniences to other module directories via relative paths
+ISAACLAB_EXPERIMENTAL_EXT_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), "../"))
+"""Path to the extension source directory."""
+
+ISAACLAB_EXPERIMENTAL_METADATA = toml.load(os.path.join(ISAACLAB_EXPERIMENTAL_EXT_DIR, "config", "extension.toml"))
+"""Extension metadata dictionary parsed from the extension.toml file."""
+
+# Configure the module-level variables
+__version__ = ISAACLAB_EXPERIMENTAL_METADATA["package"]["version"]

source/isaaclab_experimental/isaaclab_experimental/envs/__init__.py

@@ -0,0 +1,51 @@
+# Copyright (c) 2022-2026, The Isaac Lab Project Developers (https://github.com/isaac-sim/IsaacLab/blob/main/CONTRIBUTORS.md).
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Sub-package for environment definitions.
+
+Environments define the interface between the agent and the simulation.
+In the simplest case, the environment provides the agent with the current
+observations and executes the actions provided by the agent. However, the
+environment can also provide additional information such as the current
+reward, done flag, and information about the current episode.
+
+There are two types of environment designing workflows:
+
+* **Manager-based**: The environment is decomposed into individual components (or managers)
+  for different aspects (such as computing observations, applying actions, and applying
+  randomization. The users mainly configure the managers and the environment coordinates the
+  managers and calls their functions.
+* **Direct**: The user implements all the necessary functionality directly into a single class
+  directly without the need for additional managers.
+
+Based on these workflows, there are the following environment classes for single and multi-agent RL:
+
+**Single-Agent RL:**
+
+* :class:`ManagerBasedEnv`: The manager-based workflow base environment which only provides the
+  agent with the current observations and executes the actions provided by the agent.
+* :class:`ManagerBasedRLEnv`: The manager-based workflow RL task environment which besides the
+  functionality of the base environment also provides additional Markov Decision Process (MDP)
+  related information such as the current reward, done flag, and information.
+* :class:`DirectRLEnv`: The direct workflow RL task environment which provides implementations for
+  implementing scene setup, computing dones, performing resets, and computing reward and observation.
+
+**Multi-Agent RL (MARL):**
+
+* :class:`DirectMARLEnv`: The direct workflow MARL task environment which provides implementations for
+  implementing scene setup, computing dones, performing resets, and computing reward and observation.
+
+For more information about the workflow design patterns, see the `Task Design Workflows`_ section.
+
+.. _`Task Design Workflows`: https://isaac-sim.github.io/IsaacLab/source/features/task_workflows.html
+"""
+
+from .direct_rl_env_warp import DirectRLEnvWarp  # noqa: F401
+from .interactive_scene_warp import InteractiveSceneWarp  # noqa: F401
+
+__all__ = [
+    "DirectRLEnvWarp",
+    "InteractiveSceneWarp",
+]