Skip to content

Follow-up doc nits from PR #465 #476

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
cvolkcvolk merged 2 commits into from
Mar 10, 2026
Merged

Follow-up doc nits from PR #465 #476

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
15ce4ab
Use python alias and drop --headless default in RL docs
cvolkcvolk Mar 9, 2026
9731684
Merge branch 'main' into cvolk/followup-interop-5p1-nits
cvolkcvolk Mar 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/pages/example_workflows/reinforcement_learning/step_1_environment_setup.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -159,7 +159,7 @@ To validate the environment loads correctly, run one training iteration and chec

.. code-block:: bash

/isaac-sim/python.sh submodules/IsaacLab/scripts/reinforcement_learning/rsl_rl/train.py \
python submodules/IsaacLab/scripts/reinforcement_learning/rsl_rl/train.py \
--external_callback isaaclab_arena.environments.isaaclab_interop.environment_registration_callback \
--task lift_object \
--num_envs 64 \
Expand Down
16 changes: 9 additions & 7 deletions docs/pages/example_workflows/reinforcement_learning/step_2_policy_training.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,12 +14,15 @@ builds the environment, and registers it with gym so IsaacLab's script can find

.. code-block:: bash

/isaac-sim/python.sh submodules/IsaacLab/scripts/reinforcement_learning/rsl_rl/train.py \
python submodules/IsaacLab/scripts/reinforcement_learning/rsl_rl/train.py \
--external_callback isaaclab_arena.environments.isaaclab_interop.environment_registration_callback \
--task lift_object \
--num_envs 512 \
--max_iterations 12000 \
--headless
--max_iterations 12000

.. tip::

Add ``--headless`` to suppress the GUI when running on a headless server.

Checkpoints are written to ``logs/rsl_rl/generic_experiment/<timestamp>/``.
The agent configuration is saved alongside as ``params/agent.yaml``,
Expand Down Expand Up @@ -47,12 +50,11 @@ For example, to train with relu activation and a higher learning rate:

.. code-block:: bash

/isaac-sim/python.sh submodules/IsaacLab/scripts/reinforcement_learning/rsl_rl/train.py \
python submodules/IsaacLab/scripts/reinforcement_learning/rsl_rl/train.py \
--external_callback isaaclab_arena.environments.isaaclab_interop.environment_registration_callback \
--task lift_object \
--num_envs 512 \
--max_iterations 12000 \
--headless \
agent.policy.activation=relu \
agent.algorithm.learning_rate=0.001

Expand All @@ -64,7 +66,7 @@ Launch Tensorboard to monitor progress:

.. code-block:: bash

/isaac-sim/python.sh -m tensorboard.main --logdir logs/rsl_rl
python -m tensorboard.main --logdir logs/rsl_rl

During training, each iteration prints a summary to the console:

Expand Down Expand Up @@ -104,7 +106,7 @@ Add ``--distributed`` to spread environments across all available GPUs:

.. code-block:: bash

/isaac-sim/python.sh submodules/IsaacLab/scripts/reinforcement_learning/rsl_rl/train.py \
python submodules/IsaacLab/scripts/reinforcement_learning/rsl_rl/train.py \
--external_callback isaaclab_arena.environments.isaaclab_interop.environment_registration_callback \
--task lift_object \
--num_envs 512 \
Expand Down
6 changes: 3 additions & 3 deletions docs/pages/example_workflows/reinforcement_learning/step_3_evaluation.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ Method 1: Single Environment Evaluation

.. code-block:: bash

/isaac-sim/python.sh isaaclab_arena/evaluation/policy_runner.py \
python isaaclab_arena/evaluation/policy_runner.py \
--policy_type rsl_rl \
--num_steps 1000 \
--checkpoint_path logs/rsl_rl/generic_experiment/2026-01-28_17-26-10/model_11999.pt \
Expand Down Expand Up @@ -77,7 +77,7 @@ For more statistically significant results, run across many environments in para

.. code-block:: bash

/isaac-sim/python.sh isaaclab_arena/evaluation/policy_runner.py \
python isaaclab_arena/evaluation/policy_runner.py \
--policy_type rsl_rl \
--num_steps 5000 \
--num_envs 64 \
Expand Down Expand Up @@ -131,7 +131,7 @@ Create a file ``eval_config.json``:

.. code-block:: bash

/isaac-sim/python.sh isaaclab_arena/evaluation/eval_runner.py --eval_jobs_config eval_config.json
python isaaclab_arena/evaluation/eval_runner.py --eval_jobs_config eval_config.json

.. code-block:: text

Expand Down