Update Orbit-related source code and docs to Isaac Lab (#159)

* Rename Isaac Orbit loaders and wrappers files to Isaac Lab

* Rename Orbit wrapper to Isaac Lab

* Rename Orbit examples to Isaac Lab

* Update the Isaac Lab environment loader

* Rename Orbit environment loader to Isaac Lab

* Improve auto wrapper detection implementation

* Replace Orbit by Isaac Lab in docs

* Rename Orbit files to Isaac Lab in docs

* Update README

* Update CHANGELOG

CHANGELOG.md

@@ -8,6 +8,9 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 - Add support to automatically compute the write and checkpoint intervals and make it the default option
 - Single forward-pass in shared models
 
+### Changed
+- Update Orbit-related source code and docs to Isaac Lab
+
 ### Fixed
 - Move the batch sampling inside gradient step loop for DDPG and TD3
 

README.md

@@ -17,7 +17,7 @@
 <h2 align="center" style="border-bottom: 0 !important;">SKRL - Reinforcement Learning library</h2>
 <br>
 
-**skrl** is an open-source modular library for Reinforcement Learning written in Python (on top of [PyTorch](https://pytorch.org/) and [JAX](https://jax.readthedocs.io)) and designed with a focus on modularity, readability, simplicity, and transparency of algorithm implementation. In addition to supporting the OpenAI [Gym](https://www.gymlibrary.dev) / Farama [Gymnasium](https://gymnasium.farama.org) and [DeepMind](https://github.com/deepmind/dm_env) and other environment interfaces, it allows loading and configuring [NVIDIA Isaac Gym](https://developer.nvidia.com/isaac-gym/), [NVIDIA Isaac Orbit](https://isaac-orbit.github.io/orbit/index.html) and [NVIDIA Omniverse Isaac Gym](https://docs.omniverse.nvidia.com/isaacsim/latest/tutorial_gym_isaac_gym.html) environments, enabling agents' simultaneous training by scopes (subsets of environments among all available environments), which may or may not share resources, in the same run.
+**skrl** is an open-source modular library for Reinforcement Learning written in Python (on top of [PyTorch](https://pytorch.org/) and [JAX](https://jax.readthedocs.io)) and designed with a focus on modularity, readability, simplicity, and transparency of algorithm implementation. In addition to supporting the OpenAI [Gym](https://www.gymlibrary.dev) / Farama [Gymnasium](https://gymnasium.farama.org) and [DeepMind](https://github.com/deepmind/dm_env) and other environment interfaces, it allows loading and configuring [NVIDIA Isaac Gym](https://developer.nvidia.com/isaac-gym/), [NVIDIA Omniverse Isaac Gym](https://docs.omniverse.nvidia.com/isaacsim/latest/tutorial_gym_isaac_gym.html) and [NVIDIA Isaac Lab](https://isaac-sim.github.io/IsaacLab/index.html) environments, enabling agents' simultaneous training by scopes (subsets of environments among all available environments), which may or may not share resources, in the same run.
 
 <br>
 

docs/source/api/envs.rst

@@ -7,16 +7,16 @@ Environments
     Wrapping (single-agent) <envs/wrapping>
     Wrapping (multi-agents) <envs/multi_agents_wrapping>
     Isaac Gym environments <envs/isaac_gym>
-    Isaac Orbit environments <envs/isaac_orbit>
     Omniverse Isaac Gym environments <envs/omniverse_isaac_gym>
+    Isaac Lab environments <envs/isaaclab>
 
 The environment plays a fundamental and crucial role in defining the RL setup. It is the place where the agent interacts, and it is responsible for providing the agent with information about its current state, as well as the rewards/penalties associated with each action.
 
 .. raw:: html
 
     <br><hr>
 
-Grouped in this section you will find how to load environments from NVIDIA Isaac Gym, Isaac Orbit and Omniverse Isaac Gym with a simple function.
+Grouped in this section you will find how to load environments from NVIDIA Isaac Gym, Omniverse Isaac Gym and Isaac Lab with a simple function.
 
 In addition, you will be able to :doc:`wrap single-agent <envs/wrapping>` and :doc:`multi-agent <envs/multi_agents_wrapping>` RL environment interfaces.
 
@@ -29,10 +29,10 @@ In addition, you will be able to :doc:`wrap single-agent <envs/wrapping>` and :d
     * - :doc:`Isaac Gym environments <envs/isaac_gym>`
       - .. centered:: :math:`\blacksquare`
       - .. centered:: :math:`\blacksquare`
-    * - :doc:`Isaac Orbit environments <envs/isaac_orbit>`
+    * - :doc:`Omniverse Isaac Gym environments <envs/omniverse_isaac_gym>`
       - .. centered:: :math:`\blacksquare`
       - .. centered:: :math:`\blacksquare`
-    * - :doc:`Omniverse Isaac Gym environments <envs/omniverse_isaac_gym>`
+    * - :doc:`Isaac Lab environments <envs/isaaclab>`
       - .. centered:: :math:`\blacksquare`
       - .. centered:: :math:`\blacksquare`
 
@@ -57,10 +57,10 @@ In addition, you will be able to :doc:`wrap single-agent <envs/wrapping>` and :d
     * - Isaac Gym (previews)
       - .. centered:: :math:`\blacksquare`
       - .. centered:: :math:`\blacksquare`
-    * - Isaac Orbit
+    * - Omniverse Isaac Gym |_5| |_5| |_5| |_5| |_2|
       - .. centered:: :math:`\blacksquare`
       - .. centered:: :math:`\blacksquare`
-    * - Omniverse Isaac Gym |_5| |_5| |_5| |_5| |_2|
+    * - Isaac Lab
       - .. centered:: :math:`\blacksquare`
       - .. centered:: :math:`\blacksquare`
     * - PettingZoo

docs/source/api/envs/isaaclab.rst

@@ -0,0 +1,90 @@
+Isaac Lab environments
+======================
+
+.. image:: ../../_static/imgs/example_isaaclab.png
+    :width: 100%
+    :align: center
+    :alt: Isaac Lab environments
+
+.. raw:: html
+
+    <br><br><hr>
+
+Environments
+------------
+
+The repository https://github.com/isaac-sim/IsaacLab provides the example reinforcement learning environments for Isaac Lab (Orbit and Omniverse Isaac Gym unification).
+
+These environments can be easily loaded and configured by calling a single function provided with this library. This function also makes it possible to configure the environment from the command line arguments (see Isaac Lab's `Training with an RL Agent <https://isaac-sim.github.io/IsaacLab/source/tutorials/03_envs/run_rl_training.html>`_) or from its parameters (:literal:`task_name`, :literal:`num_envs`, :literal:`headless`, and :literal:`cli_args`).
+
+.. note::
+
+    The command line arguments has priority over the function parameters.
+
+.. note::
+
+    Isaac Lab environments implement a functionality to get their configuration from the command line. Setting the :literal:`headless` option from the trainer configuration will not work. In this case, it is necessary to set the load function's :literal:`headless` argument to True or to invoke the scripts as follows: :literal:`isaaclab -p script.py --headless`.
+
+.. raw:: html
+
+    <br>
+
+Usage
+^^^^^
+
+.. tabs::
+
+    .. tab:: Function parameters
+
+        .. tabs::
+
+            .. group-tab:: |_4| |pytorch| |_4|
+
+                .. literalinclude:: ../../snippets/loaders.py
+                    :language: python
+                    :emphasize-lines: 2, 5
+                    :start-after: [start-isaaclab-envs-parameters-torch]
+                    :end-before: [end-isaaclab-envs-parameters-torch]
+
+            .. group-tab:: |_4| |jax| |_4|
+
+                .. literalinclude:: ../../snippets/loaders.py
+                    :language: python
+                    :emphasize-lines: 2, 5
+                    :start-after: [start-isaaclab-envs-parameters-jax]
+                    :end-before: [end-isaaclab-envs-parameters-jax]
+
+    .. tab:: Command line arguments (priority)
+
+        .. tabs::
+
+            .. group-tab:: |_4| |pytorch| |_4|
+
+                .. literalinclude:: ../../snippets/loaders.py
+                    :language: python
+                    :emphasize-lines: 2, 5
+                    :start-after: [start-isaaclab-envs-cli-torch]
+                    :end-before: [end-isaaclab-envs-cli-torch]
+
+            .. group-tab:: |_4| |jax| |_4|
+
+                .. literalinclude:: ../../snippets/loaders.py
+                    :language: python
+                    :emphasize-lines: 2, 5
+                    :start-after: [start-isaaclab-envs-cli-jax]
+                    :end-before: [end-isaaclab-envs-cli-jax]
+
+        Run the main script passing the configuration as command line arguments. For example:
+
+        .. code-block::
+
+            isaaclab -p main.py --task Isaac-Cartpole-v0
+
+.. raw:: html
+
+    <br>
+
+API
+^^^
+
+.. autofunction:: skrl.envs.loaders.torch.load_isaaclab_env

docs/source/api/envs/wrapping.rst

@@ -14,8 +14,8 @@ This library works with a common API to interact with the following RL environme
 * `DeepMind <https://github.com/deepmind/dm_env>`_
 * `robosuite <https://robosuite.ai/>`_
 * `NVIDIA Isaac Gym <https://developer.nvidia.com/isaac-gym>`_ (preview 2, 3 and 4)
-* `NVIDIA Isaac Orbit <https://isaac-orbit.github.io/orbit/index.html>`_
 * `NVIDIA Omniverse Isaac Gym <https://docs.omniverse.nvidia.com/isaacsim/latest/tutorial_gym_isaac_gym.html>`_
+* `NVIDIA Isaac Lab <https://isaac-sim.github.io/IsaacLab/index.html>`_
 
 To operate with them and to support interoperability between these non-compatible interfaces, a **wrapping mechanism is provided** as shown in the diagram below
 
@@ -44,6 +44,24 @@ Usage
 
 .. tabs::
 
+    .. tab:: Isaac Lab
+
+        .. tabs::
+
+            .. group-tab:: |_4| |pytorch| |_4|
+
+                .. literalinclude:: ../../snippets/wrapping.py
+                    :language: python
+                    :start-after: [pytorch-start-isaaclab]
+                    :end-before: [pytorch-end-isaaclab]
+
+            .. group-tab:: |_4| |jax| |_4|
+
+                .. literalinclude:: ../../snippets/wrapping.py
+                    :language: python
+                    :start-after: [jax-start-isaaclab]
+                    :end-before: [jax-end-isaaclab]
+
     .. tab:: Omniverse Isaac Gym
 
         .. tabs::
@@ -84,24 +102,6 @@ Usage
                             :start-after: [jax-start-omniverse-isaacgym-mt]
                             :end-before: [jax-end-omniverse-isaacgym-mt]
 
-    .. tab:: Isaac Orbit
-
-        .. tabs::
-
-            .. group-tab:: |_4| |pytorch| |_4|
-
-                .. literalinclude:: ../../snippets/wrapping.py
-                    :language: python
-                    :start-after: [pytorch-start-isaac-orbit]
-                    :end-before: [pytorch-end-isaac-orbit]
-
-            .. group-tab:: |_4| |jax| |_4|
-
-                .. literalinclude:: ../../snippets/wrapping.py
-                    :language: python
-                    :start-after: [jax-start-isaac-orbit]
-                    :end-before: [jax-end-isaac-orbit]
-
     .. tab:: Isaac Gym
 
         .. tabs::
@@ -365,7 +365,7 @@ Internal API (PyTorch)
 
     .. automethod:: __init__
 
-.. autoclass:: skrl.envs.wrappers.torch.IsaacOrbitWrapper
+.. autoclass:: skrl.envs.wrappers.torch.IsaacLabWrapper
     :undoc-members:
     :show-inheritance:
     :members:
@@ -443,7 +443,7 @@ Internal API (JAX)
 
     .. automethod:: __init__
 
-.. autoclass:: skrl.envs.wrappers.jax.IsaacOrbitWrapper
+.. autoclass:: skrl.envs.wrappers.jax.IsaacLabWrapper
     :undoc-members:
     :show-inheritance:
     :members:

docs/source/api/utils/omniverse_isaacgym_utils.rst

@@ -17,7 +17,7 @@ Control of robotic manipulators
 Differential inverse kinematics
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-This implementation attempts to unify under a single and reusable function the whole set of procedures used to compute the inverse kinematics of a robotic manipulator, originally shown in the Isaac Orbit framework's task space controllers section, but this time for Omniverse Isaac Gym.
+This implementation attempts to unify under a single and reusable function the whole set of procedures used to compute the inverse kinematics of a robotic manipulator, originally shown in the Isaac Lab (Orbit then) framework's task space controllers section, but this time for Omniverse Isaac Gym.
 
 :math:`\Delta\theta =` :guilabel:`scale` :math:`J^\dagger \, \vec{e}`
 

docs/source/examples/isaacorbit/jax_ant_ddpg.py → docs/source/examples/isaaclab/jax_ant_ddpg.py

@@ -19,7 +19,7 @@
 # import the skrl components to build the RL system
 from skrl import config
 from skrl.agents.jax.ddpg import DDPG, DDPG_DEFAULT_CONFIG
-from skrl.envs.loaders.jax import load_isaac_orbit_env
+from skrl.envs.loaders.jax import load_isaaclab_env
 from skrl.envs.wrappers.jax import wrap_env
 from skrl.memories.jax import RandomMemory
 from skrl.models.jax import DeterministicMixin, Model
@@ -69,8 +69,8 @@ def __call__(self, inputs, role):
         return x, {}
 
 
-# load and wrap the Isaac Orbit environment
-env = load_isaac_orbit_env(task_name="Isaac-Ant-v0", num_envs=64)
+# load and wrap the Isaac Lab environment
+env = load_isaaclab_env(task_name="Isaac-Ant-v0", num_envs=64)
 env = wrap_env(env)
 
 device = env.device

docs/source/examples/isaacorbit/jax_ant_ppo.py → docs/source/examples/isaaclab/jax_ant_ppo.py

@@ -19,7 +19,7 @@
 # import the skrl components to build the RL system
 from skrl import config
 from skrl.agents.jax.ppo import PPO, PPO_DEFAULT_CONFIG
-from skrl.envs.loaders.jax import load_isaac_orbit_env
+from skrl.envs.loaders.jax import load_isaaclab_env
 from skrl.envs.wrappers.jax import wrap_env
 from skrl.memories.jax import RandomMemory
 from skrl.models.jax import DeterministicMixin, GaussianMixin, Model
@@ -72,8 +72,8 @@ def __call__(self, inputs, role):
         return x, {}
 
 
-# load and wrap the Isaac Orbit environment
-env = load_isaac_orbit_env(task_name="Isaac-Ant-v0")
+# load and wrap the Isaac Lab environment
+env = load_isaaclab_env(task_name="Isaac-Ant-v0")
 env = wrap_env(env)
 
 device = env.device

docs/source/examples/isaacorbit/jax_ant_sac.py → docs/source/examples/isaaclab/jax_ant_sac.py

@@ -19,7 +19,7 @@
 # import the skrl components to build the RL system
 from skrl import config
 from skrl.agents.jax.sac import SAC, SAC_DEFAULT_CONFIG
-from skrl.envs.loaders.jax import load_isaac_orbit_env
+from skrl.envs.loaders.jax import load_isaaclab_env
 from skrl.envs.wrappers.jax import wrap_env
 from skrl.memories.jax import RandomMemory
 from skrl.models.jax import DeterministicMixin, GaussianMixin, Model
@@ -70,8 +70,8 @@ def __call__(self, inputs, role):
         return x, {}
 
 
-# load and wrap the Isaac Orbit environment
-env = load_isaac_orbit_env(task_name="Isaac-Ant-v0", num_envs=64)
+# load and wrap the Isaac Lab environment
+env = load_isaaclab_env(task_name="Isaac-Ant-v0", num_envs=64)
 env = wrap_env(env)
 
 device = env.device