diff --git a/docs/source/features/hydra.rst b/docs/source/features/hydra.rst index bda92e82a563..06552b2ef7e3 100644 --- a/docs/source/features/hydra.rst +++ b/docs/source/features/hydra.rst @@ -25,30 +25,30 @@ As a result, training with hydra arguments can be run with the following syntax: .. code-block:: shell - ./isaaclab.sh train --rl_library rsl_rl --task=Isaac-Cartpole --headless env.actions.joint_effort.scale=10.0 agent.seed=2024 + ./isaaclab.sh train --rl_library rsl_rl --task=Isaac-Cartpole-v0 --headless env.actions.joint_effort.scale=10.0 agent.seed=2024 .. tab-item:: rl_games :sync: rl_games .. code-block:: shell - ./isaaclab.sh train --rl_library rl_games --task=Isaac-Cartpole --headless env.actions.joint_effort.scale=10.0 agent.params.seed=2024 + ./isaaclab.sh train --rl_library rl_games --task=Isaac-Cartpole-v0 --headless env.actions.joint_effort.scale=10.0 agent.params.seed=2024 .. tab-item:: skrl :sync: skrl .. code-block:: shell - ./isaaclab.sh train --rl_library skrl --task=Isaac-Cartpole --headless env.actions.joint_effort.scale=10.0 agent.seed=2024 + ./isaaclab.sh train --rl_library skrl --task=Isaac-Cartpole-v0 --headless env.actions.joint_effort.scale=10.0 agent.seed=2024 .. tab-item:: sb3 :sync: sb3 .. code-block:: shell - ./isaaclab.sh train --rl_library sb3 --task=Isaac-Cartpole --headless env.actions.joint_effort.scale=10.0 agent.seed=2024 + ./isaaclab.sh train --rl_library sb3 --task=Isaac-Cartpole-v0 --headless env.actions.joint_effort.scale=10.0 agent.seed=2024 -The above command will run training with the task ``Isaac-Cartpole`` in headless mode, and set the +The above command will run training with the task ``Isaac-Cartpole-v0`` in headless mode, and set the ``env.actions.joint_effort.scale`` parameter to 10.0 and the ``agent.seed`` parameter to 2024. .. note:: @@ -418,8 +418,8 @@ for that task, grouped by selector type: .. code-block:: bash - ./isaaclab.sh train --rl_library rsl_rl \ - --task Isaac-Cartpole-Camera-Direct --help + ./isaaclab.sh train --rl_library rl_games \ + --task Isaac-Cartpole-Camera-Presets-Direct-v0 --help .. note:: diff --git a/docs/source/how-to/profile_with_nsys.rst b/docs/source/how-to/profile_with_nsys.rst index f0369e8c6db4..210f6489bf31 100644 --- a/docs/source/how-to/profile_with_nsys.rst +++ b/docs/source/how-to/profile_with_nsys.rst @@ -43,7 +43,7 @@ The following command shows how to capture a profile for the ``Isaac-Cartpole-v0 --python-functions-trace=scripts/benchmarks/nsys_trace.json \ -o my_profile \ ./isaaclab.sh train --rl_library rsl_rl \ - --task=Isaac-Cartpole \ + --task=Isaac-Cartpole-v0 \ --headless \ --max_iterations=3 diff --git a/docs/source/how-to/record_video.rst b/docs/source/how-to/record_video.rst index fa92c66b0fb7..437a14b192d1 100644 --- a/docs/source/how-to/record_video.rst +++ b/docs/source/how-to/record_video.rst @@ -21,7 +21,7 @@ Example usage: .. code-block:: shell - ./isaaclab.sh train --rl_library rl_games --task=Isaac-Cartpole --headless --video --video_length 100 --video_interval 500 + ./isaaclab.sh train --rl_library rl_games --task=Isaac-Cartpole-v0 --headless --video --video_length 100 --video_interval 500 The recorded videos will be saved in the same directory as the training checkpoints, under diff --git a/docs/source/migration/migrating_from_isaacgymenvs.rst b/docs/source/migration/migrating_from_isaacgymenvs.rst index 804a0cc2f1db..8deadd5baa1e 100644 --- a/docs/source/migration/migrating_from_isaacgymenvs.rst +++ b/docs/source/migration/migrating_from_isaacgymenvs.rst @@ -916,7 +916,7 @@ To launch a training in Isaac Lab, use the command: .. code-block:: bash - ./isaaclab.sh train --rl_library rl_games --task=Isaac-Cartpole-Direct --headless + ./isaaclab.sh train --rl_library rl_games --task=Isaac-Cartpole-Direct-v0 --headless Launching Inferencing ~~~~~~~~~~~~~~~~~~~~~ @@ -925,7 +925,7 @@ To launch inferencing in Isaac Lab, use the command: .. code-block:: bash - ./isaaclab.sh play --rl_library rl_games --task=Isaac-Cartpole-Direct --num_envs=25 --checkpoint= + ./isaaclab.sh play --rl_library rl_games --task=Isaac-Cartpole-Direct-v0 --num_envs=25 --checkpoint= Additional Resources diff --git a/docs/source/migration/migrating_from_omniisaacgymenvs.rst b/docs/source/migration/migrating_from_omniisaacgymenvs.rst index 5d37c4e6a5d1..25d007c99b0a 100644 --- a/docs/source/migration/migrating_from_omniisaacgymenvs.rst +++ b/docs/source/migration/migrating_from_omniisaacgymenvs.rst @@ -983,7 +983,7 @@ To launch a training in Isaac Lab, use the command: .. code-block:: bash - ./isaaclab.sh train --rl_library rl_games --task=Isaac-Cartpole-Direct --headless + ./isaaclab.sh train --rl_library rl_games --task=Isaac-Cartpole-Direct-v0 --headless Launching Inferencing ~~~~~~~~~~~~~~~~~~~~~ @@ -992,7 +992,7 @@ To launch inferencing in Isaac Lab, use the command: .. code-block:: bash - ./isaaclab.sh play --rl_library rl_games --task=Isaac-Cartpole-Direct --num_envs=25 --checkpoint= + ./isaaclab.sh play --rl_library rl_games --task=Isaac-Cartpole-Direct-v0 --num_envs=25 --checkpoint= .. _`OmniIsaacGymEnvs`: https://github.com/isaac-sim/OmniIsaacGymEnvs diff --git a/docs/source/migration/migrating_to_isaaclab_3-0.rst b/docs/source/migration/migrating_to_isaaclab_3-0.rst index 4047266a2f11..d5150ef7f515 100644 --- a/docs/source/migration/migrating_to_isaaclab_3-0.rst +++ b/docs/source/migration/migrating_to_isaaclab_3-0.rst @@ -45,16 +45,16 @@ and play. Instead of launching library-specific scripts under .. code-block:: bash # Isaac Lab 2.x/deprecated - ./isaaclab.sh -p scripts/reinforcement_learning/rsl_rl/train.py --task Isaac-Cartpole --headless + ./isaaclab.sh -p scripts/reinforcement_learning/rsl_rl/train.py --task Isaac-Cartpole-v0 --headless # Isaac Lab 3.0 - ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole --headless + ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole-v0 --headless The same pattern applies to the play workflow: .. code-block:: bash - ./isaaclab.sh play --rl_library rsl_rl --task Isaac-Cartpole --checkpoint /PATH/TO/model.pt + ./isaaclab.sh play --rl_library rsl_rl --task Isaac-Cartpole-v0 --checkpoint /PATH/TO/model.pt Supported reinforcement learning libraries are ``rsl_rl``, ``rl_games``, ``skrl``, ``sb3``, and ``rlinf``. The old per-library ``train.py`` and ``play.py`` scripts @@ -67,7 +67,7 @@ script path and pass ``--rl_library`` to it: .. code-block:: bash python -m torch.distributed.run --nproc_per_node=2 scripts/reinforcement_learning/train.py \ - --rl_library rsl_rl --task Isaac-Cartpole --headless --distributed + --rl_library rsl_rl --task Isaac-Cartpole-v0 --headless --distributed Multi-Backend Architecture diff --git a/docs/source/overview/core-concepts/physical-backends/newton/kamino-solver.rst b/docs/source/overview/core-concepts/physical-backends/newton/kamino-solver.rst index c1da1354c362..1ede9f509060 100644 --- a/docs/source/overview/core-concepts/physical-backends/newton/kamino-solver.rst +++ b/docs/source/overview/core-concepts/physical-backends/newton/kamino-solver.rst @@ -66,13 +66,13 @@ You can select the preset globally: .. code-block:: bash - ./isaaclab.sh train --rl_library rsl_rl --task=Isaac-Cartpole physics=newton_kamino + ./isaaclab.sh train --rl_library rsl_rl --task=Isaac-Cartpole-v0 physics=newton_kamino or select the physics field directly: .. code-block:: bash - ./isaaclab.sh train --rl_library rsl_rl --task=Isaac-Cartpole env.sim.physics=newton_kamino + ./isaaclab.sh train --rl_library rsl_rl --task=Isaac-Cartpole-v0 env.sim.physics=newton_kamino Use the direct path override when only one task field should use the Kamino preset. Use ``physics=newton_kamino`` when you want every matching preset field in the task config diff --git a/docs/source/overview/core-concepts/sensors/camera.rst b/docs/source/overview/core-concepts/sensors/camera.rst index 303b50aa8ee9..5750f6f8210a 100644 --- a/docs/source/overview/core-concepts/sensors/camera.rst +++ b/docs/source/overview/core-concepts/sensors/camera.rst @@ -174,7 +174,7 @@ When using the RTX renderer, add ``--enable_cameras`` when launching: .. code-block:: shell ./isaaclab.sh train --rl_library rl_games \ - --task=Isaac-Cartpole-Camera-Direct --headless --enable_cameras + --task=Isaac-Cartpole-Camera-Presets-Direct-v0 --headless --enable_cameras Annotators (RTX only) diff --git a/docs/source/overview/core-concepts/visualization.rst b/docs/source/overview/core-concepts/visualization.rst index d2d3c0986be3..4b4c5afa06e1 100644 --- a/docs/source/overview/core-concepts/visualization.rst +++ b/docs/source/overview/core-concepts/visualization.rst @@ -70,20 +70,20 @@ Launch visualizers from the command line with ``--visualizer`` (or ``--viz`` ali .. code-block:: bash # Launch all visualizers (comma-delimited list, no spaces) - ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole --viz kit,newton,rerun + ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole-v0 --viz kit,newton,rerun # Launch only the Newton visualizer - ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole --viz newton + ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole-v0 --viz newton # Launch the Viser web-based visualizer - ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole --viz viser + ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole-v0 --viz viser To run in headless mode, omit the ``--viz`` argument: .. code-block:: bash - ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole + ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole-v0 .. note:: @@ -230,7 +230,7 @@ Note, Kit tiled camera views require launching with ``--enable_cameras``. - The visualizer displays existing Isaac Lab ``Camera`` sensor output. Generated-camera fields such as ``tiled_cam_eye`` and ``tiled_cam_target_prim_path`` are ignored. Note that the ``tiled_cam_prim_path`` has a default value, but different environments may require different paths. This mode requires an environment that registers Isaac Lab ``Camera`` sensors - in ``scene.sensors``. For Cartpole, use a camera task such as ``Isaac-Cartpole-Camera``. The plain ``Isaac-Cartpole`` + in ``scene.sensors``. For Cartpole, use a camera task such as ``Isaac-Cartpole-Camera-Presets-Direct-v0``. The plain ``Isaac-Cartpole-v0`` task has no ``/World/envs/*/Camera`` sensor, so leave ``tiled_cam_prim_path=None`` to use generated visualizer cameras. **How to Access the Tiled Camera View in the UI** @@ -603,7 +603,7 @@ the num of environments can be overwritten and decreased using ``--num_envs``: .. code-block:: bash - ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole --viz rerun --num_envs 512 + ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole-v0 --viz rerun --num_envs 512 **Rerun Visualizer FPS Control** diff --git a/docs/source/overview/reinforcement-learning/rl_existing_scripts.rst b/docs/source/overview/reinforcement-learning/rl_existing_scripts.rst index 33148f28c912..ae3c79cba678 100644 --- a/docs/source/overview/reinforcement-learning/rl_existing_scripts.rst +++ b/docs/source/overview/reinforcement-learning/rl_existing_scripts.rst @@ -18,13 +18,13 @@ See :doc:`/source/features/hydra` for all available names and how the selectors --task --headless physics=newton_mjwarp # Switch renderer (camera environments) - ./isaaclab.sh train --rl_library rsl_rl \ - --task Isaac-Cartpole-Camera-Direct --headless \ + ./isaaclab.sh train --rl_library rl_games \ + --task Isaac-Cartpole-Camera-Presets-Direct-v0 --headless \ --enable_cameras renderer=newton_renderer # Combine selectors freely - ./isaaclab.sh train --rl_library rsl_rl \ - --task Isaac-Cartpole-Camera-Direct --headless \ + ./isaaclab.sh train --rl_library rl_games \ + --task Isaac-Cartpole-Camera-Presets-Direct-v0 --headless \ --enable_cameras physics=newton_mjwarp renderer=newton_renderer presets=rgb .. note:: diff --git a/docs/source/setup/installation/cloud_installation.rst b/docs/source/setup/installation/cloud_installation.rst index 6ed54570f174..bd999d8bb036 100644 --- a/docs/source/setup/installation/cloud_installation.rst +++ b/docs/source/setup/installation/cloud_installation.rst @@ -154,7 +154,7 @@ To run Isaac Lab commands, open a terminal on the workstation: .. code-block:: bash ~/IsaacLab/isaaclab.sh train --rl_library rsl_rl \ - --task=Isaac-Cartpole-Direct --headless + --task=Isaac-Cartpole-Direct-v0 --headless Pausing and Resuming diff --git a/docs/source/setup/installation/kitless_installation.rst b/docs/source/setup/installation/kitless_installation.rst index 76486b2afc17..6f68a4a36429 100644 --- a/docs/source/setup/installation/kitless_installation.rst +++ b/docs/source/setup/installation/kitless_installation.rst @@ -34,7 +34,7 @@ and kickoff training with MJWarp physics and the Newton visualizer: # Kickoff training with MJWarp physics and Newton visualizer ./isaaclab.sh train --rl_library rsl_rl \ - --task=Isaac-Cartpole-Direct \ + --task=Isaac-Cartpole-Direct-v0 \ --num_envs=16 --max_iterations=10 \ physics=newton_mjwarp --visualizer newton @@ -49,7 +49,7 @@ and kickoff training with MJWarp physics and the Newton visualizer: :: Kickoff training with MJWarp physics and Newton visualizer isaaclab.bat train --rl_library rsl_rl ^ - --task=Isaac-Cartpole-Direct ^ + --task=Isaac-Cartpole-Direct-v0 ^ --num_envs=16 --max_iterations=10 ^ physics=newton_mjwarp --visualizer newton diff --git a/docs/source/setup/quickstart.rst b/docs/source/setup/quickstart.rst index b1d98453fbb0..403936bf7c61 100644 --- a/docs/source/setup/quickstart.rst +++ b/docs/source/setup/quickstart.rst @@ -88,19 +88,19 @@ Use the reinforcement learning training command with a **task name** and # Kit-less: Newton MJWarp physics + Newton visualizer ./isaaclab.sh train --rl_library rsl_rl \ - --task=Isaac-Cartpole-Direct \ + --task=Isaac-Cartpole-Direct-v0 \ --num_envs=16 --max_iterations=10 \ physics=newton_mjwarp --visualizer newton # With Isaac Sim: PhysX physics (default renderer) ./isaaclab.sh train --rl_library rsl_rl \ - --task=Isaac-Cartpole-Direct \ + --task=Isaac-Cartpole-Direct-v0 \ --num_envs=4096 \ physics=physx # Camera task: typed physics + renderer + domain preset - ./isaaclab.sh train --rl_library rsl_rl \ - --task=Isaac-Cartpole-Camera-Direct \ + ./isaaclab.sh train --rl_library rl_games \ + --task=Isaac-Cartpole-RGB-Camera-Direct-v0 \ physics=newton_mjwarp renderer=newton_renderer presets=rgb .. tab-item:: :icon:`fa-brands fa-windows` Windows @@ -109,12 +109,12 @@ Use the reinforcement learning training command with a **task name** and .. code-block:: batch isaaclab.bat train --rl_library rsl_rl ^ - --task=Isaac-Cartpole-Direct ^ + --task=Isaac-Cartpole-Direct-v0 ^ --num_envs=16 --max_iterations=10 ^ physics=newton_mjwarp --visualizer newton isaaclab.bat train --rl_library rsl_rl ^ - --task=Isaac-Cartpole-Direct ^ + --task=Isaac-Cartpole-Direct-v0 ^ --num_envs=4096 ^ physics=physx diff --git a/docs/source/setup/quickstart_details.rst b/docs/source/setup/quickstart_details.rst index 7f4858494a10..5bce9217e953 100644 --- a/docs/source/setup/quickstart_details.rst +++ b/docs/source/setup/quickstart_details.rst @@ -34,19 +34,19 @@ options (observation modes, camera configs, etc.). They fold into Hydra override # Kit-less: Newton MJWarp + Newton visualizer ./isaaclab.sh train --rl_library rsl_rl \ - --task=Isaac-Cartpole-Direct \ + --task=Isaac-Cartpole-Direct-v0 \ --num_envs=4096 \ physics=newton_mjwarp --visualizer newton # With Isaac Sim: PhysX ./isaaclab.sh train --rl_library rsl_rl \ - --task=Isaac-Cartpole-Direct \ + --task=Isaac-Cartpole-Direct-v0 \ --num_envs=4096 \ physics=physx # Camera task: physics + renderer + domain preset - ./isaaclab.sh train --rl_library rsl_rl \ - --task=Isaac-Cartpole-Camera-Direct \ + ./isaaclab.sh train --rl_library rl_games \ + --task=Isaac-Cartpole-Camera-Presets-Direct-v0 \ physics=newton_mjwarp renderer=newton_renderer presets=rgb # OVRTX rendering (kit-less, no Kit visualizer) @@ -61,7 +61,7 @@ options (observation modes, camera configs, etc.). They fold into Hydra override .. code-block:: batch isaaclab.bat train --rl_library rsl_rl ^ - --task=Isaac-Cartpole-Direct ^ + --task=Isaac-Cartpole-Direct-v0 ^ --num_envs=4096 ^ physics=newton_mjwarp --visualizer newton diff --git a/docs/source/tutorials/03_envs/configuring_rl_training.rst b/docs/source/tutorials/03_envs/configuring_rl_training.rst index 37306701a526..94b382163e7d 100644 --- a/docs/source/tutorials/03_envs/configuring_rl_training.rst +++ b/docs/source/tutorials/03_envs/configuring_rl_training.rst @@ -113,7 +113,7 @@ we can use the ``--agent`` argument to specify the configuration instance to use .. code-block:: bash # standard PPO training - ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole --headless \ + ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole-v0 --headless \ --run_name ppo * Training with the PPO configuration with symmetry augmentation: @@ -121,12 +121,12 @@ we can use the ``--agent`` argument to specify the configuration instance to use .. code-block:: bash # PPO training with symmetry augmentation - ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole --headless \ + ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole-v0 --headless \ --agent rsl_rl_with_symmetry_cfg_entry_point \ --run_name ppo_with_symmetry_data_augmentation # you can use hydra to disable symmetry augmentation but enable mirror loss computation - ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole --headless \ + ./isaaclab.sh train --rl_library rsl_rl --task Isaac-Cartpole-v0 --headless \ --agent rsl_rl_with_symmetry_cfg_entry_point \ --run_name ppo_without_symmetry_data_augmentation \ agent.algorithm.symmetry_cfg.use_data_augmentation=false diff --git a/docs/source/tutorials/03_envs/create_direct_rl_env.rst b/docs/source/tutorials/03_envs/create_direct_rl_env.rst index 4957726a8686..260f4095b41a 100644 --- a/docs/source/tutorials/03_envs/create_direct_rl_env.rst +++ b/docs/source/tutorials/03_envs/create_direct_rl_env.rst @@ -205,7 +205,7 @@ To run training for the direct workflow Cartpole environment, we can use the fol .. code-block:: bash - ./isaaclab.sh train --rl_library rl_games --task=Isaac-Cartpole-Direct + ./isaaclab.sh train --rl_library rl_games --task=Isaac-Cartpole-Direct-v0 .. figure:: ../../_static/tutorials/tutorial_create_direct_workflow.jpg :align: center diff --git a/docs/source/tutorials/03_envs/run_rl_training.rst b/docs/source/tutorials/03_envs/run_rl_training.rst index 38bc7d9af57d..dd8e8f3bc28c 100644 --- a/docs/source/tutorials/03_envs/run_rl_training.rst +++ b/docs/source/tutorials/03_envs/run_rl_training.rst @@ -88,7 +88,7 @@ Rendering can still be active for sensor/camera data capture when enabled by the .. code-block:: bash - ./isaaclab.sh train --rl_library sb3 --task Isaac-Cartpole --num_envs 64 + ./isaaclab.sh train --rl_library sb3 --task Isaac-Cartpole-v0 --num_envs 64 Headless execution with off-screen render @@ -100,7 +100,7 @@ in the workflow and pass ``--video`` to record the agent behavior. .. code-block:: bash - ./isaaclab.sh train --rl_library sb3 --task Isaac-Cartpole --num_envs 64 --video + ./isaaclab.sh train --rl_library sb3 --task Isaac-Cartpole-v0 --num_envs 64 --video The videos are saved to the ``logs/sb3/Isaac-Cartpole-v0//videos/train`` directory. You can open these videos using any video player. @@ -116,7 +116,7 @@ training command as follows: .. code-block:: bash - ./isaaclab.sh train --rl_library sb3 --task Isaac-Cartpole --num_envs 64 --viz kit + ./isaaclab.sh train --rl_library sb3 --task Isaac-Cartpole-v0 --num_envs 64 --viz kit This will open the Kit visualizer window and you can see the agent training in the environment. However, this can slow down the training process because interactive visual feedback is enabled. As a workaround, you @@ -142,7 +142,7 @@ Once the training is complete, you can visualize the trained agent by executing .. code:: bash # execute from the root directory of the repository - ./isaaclab.sh play --rl_library sb3 --task Isaac-Cartpole --num_envs 32 --viz kit + ./isaaclab.sh play --rl_library sb3 --task Isaac-Cartpole-v0 --num_envs 32 --viz kit The above command will load the latest checkpoint from the ``logs/sb3/Isaac-Cartpole-v0`` directory. You can also specify a specific checkpoint by passing the ``--checkpoint`` flag.