From a6dc194c387d581932749e2308da51d865aefe9d Mon Sep 17 00:00:00 2001 From: Antoine Richard Date: Wed, 10 Jun 2026 16:03:43 +0200 Subject: [PATCH] docs: Address headless cleanup review comments --- docs/source/features/hydra.rst | 4 ++-- docs/source/how-to/save_camera_output.rst | 2 +- .../core-concepts/physical-backends/ovphysx/index.rst | 2 +- docs/source/policy_deployment/00_hover/hover_policy.rst | 6 +++--- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/docs/source/features/hydra.rst b/docs/source/features/hydra.rst index f7db20129b8..8e252328ff2 100644 --- a/docs/source/features/hydra.rst +++ b/docs/source/features/hydra.rst @@ -48,8 +48,8 @@ As a result, training with hydra arguments can be run with the following syntax: ./isaaclab.sh train --rl_library sb3 --task=Isaac-Cartpole 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 -``env.actions.joint_effort.scale`` parameter to 10.0 and the ``agent.seed`` parameter to 2024. +The above command will run training with the task ``Isaac-Cartpole`` without selecting a visualizer, +and set the ``env.actions.joint_effort.scale`` parameter to 10.0 and the ``agent.seed`` parameter to 2024. .. note:: diff --git a/docs/source/how-to/save_camera_output.rst b/docs/source/how-to/save_camera_output.rst index c8174bb75ea..db155132778 100644 --- a/docs/source/how-to/save_camera_output.rst +++ b/docs/source/how-to/save_camera_output.rst @@ -94,7 +94,7 @@ To run the accompanying script, execute the following command: # Usage with saving and drawing python scripts/tutorials/04_sensors/run_usd_camera.py --save --draw --enable_cameras - # Usage with saving only in headless mode + # Usage with saving only (no visualizer) python scripts/tutorials/04_sensors/run_usd_camera.py --save --enable_cameras diff --git a/docs/source/overview/core-concepts/physical-backends/ovphysx/index.rst b/docs/source/overview/core-concepts/physical-backends/ovphysx/index.rst index 72db1343c95..63f93c1c9d6 100644 --- a/docs/source/overview/core-concepts/physical-backends/ovphysx/index.rst +++ b/docs/source/overview/core-concepts/physical-backends/ovphysx/index.rst @@ -112,7 +112,7 @@ syntax as the other backends: ./isaaclab.sh -p scripts/environments/zero_agent.py --task Isaac-Cartpole-Direct --num_envs 128 presets=ovphysx -This command starts a headless zero-action rollout; stop it with ``Ctrl+C`` +This command starts a zero-action rollout without selecting a visualizer; stop it with ``Ctrl+C`` after the environment has started and stepped successfully. Status and follow-up diff --git a/docs/source/policy_deployment/00_hover/hover_policy.rst b/docs/source/policy_deployment/00_hover/hover_policy.rst index b3233a4b689..9322bf7fe7f 100644 --- a/docs/source/policy_deployment/00_hover/hover_policy.rst +++ b/docs/source/policy_deployment/00_hover/hover_policy.rst @@ -59,7 +59,7 @@ Execute the following command from the ``HOVER`` directory to train the teacher ${ISAACLAB_PATH:?}/isaaclab.sh -p scripts/rsl_rl/train_teacher_policy.py \ --num_envs 1024 \ - --reference_motion_path neural_wbc/data/data/motions/stable_punch.pkl \ + --reference_motion_path neural_wbc/data/data/motions/stable_punch.pkl The teacher policy is trained for 10000000 iterations, or until the user interrupts the training. The resulting checkpoint is stored in ``neural_wbc/data/data/policy/h1:teacher/`` and the filename is ``model_.pt``. @@ -74,7 +74,7 @@ Execute the following command from the ``HOVER`` directory to train the student --num_envs 1024 \ --reference_motion_path neural_wbc/data/data/motions/stable_punch.pkl \ --teacher_policy.resume_path neural_wbc/data/data/policy/h1:teacher \ - --teacher_policy.checkpoint model_.pt \ + --teacher_policy.checkpoint model_.pt This assumes that you have already trained the teacher policy as there is no provided teacher policy in the repo. @@ -167,7 +167,7 @@ To deploy the trained policy on the H1 robot, --reference_motion_path neural_wbc/data/data/motions/.pkl \ --robot unitree_h1 \ --max_iterations 5000 \ - --num_envs 1 \ + --num_envs 1 .. note::