Skip to content
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

Jump to bottom

Fixes docstring in reward functions and code block in documentation #661

Merged
merged 4 commits into from
Jul 17, 2024
Merged

Fixes docstring in reward functions and code block in documentation #661

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3b61483
Fixes slash in the sample documentation
fan-ziqi Jul 6, 2024
7c0b316
Fixes norm description of joint_acc_l2
fan-ziqi Jul 9, 2024
4a2703e
Update docstring in mdp rewards
Dhoeller19 Jul 17, 2024
1fcdeba
Merge branch 'main' into devel-docs
Dhoeller19 Jul 17, 2024
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/source/setup/sample.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,7 @@ format.

.. code:: bash

./isaaclab.sh -p source/standalone//workflows/robomimic/play.py --task Isaac-Lift-Cube-Franka-IK-Rel-v0 --checkpoint /PATH/TO/model.pth
./isaaclab.sh -p source/standalone/workflows/robomimic/play.py --task Isaac-Lift-Cube-Franka-IK-Rel-v0 --checkpoint /PATH/TO/model.pth

Reinforcement Learning
~~~~~~~~~~~~~~~~~~~~~~
Expand Down
24 changes: 12 additions & 12 deletions source/extensions/omni.isaac.lab/omni/isaac/lab/envs/mdp/rewards.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,21 +74,21 @@ def __call__(self, env: ManagerBasedRLEnv, term_keys: str | list[str] = ".*") ->


def lin_vel_z_l2(env: ManagerBasedRLEnv, asset_cfg: SceneEntityCfg = SceneEntityCfg("robot")) -> torch.Tensor:
"""Penalize z-axis base linear velocity using L2-kernel."""
"""Penalize z-axis base linear velocity using L2 squared kernel."""
# extract the used quantities (to enable type-hinting)
asset: RigidObject = env.scene[asset_cfg.name]
return torch.square(asset.data.root_lin_vel_b[:, 2])


def ang_vel_xy_l2(env: ManagerBasedRLEnv, asset_cfg: SceneEntityCfg = SceneEntityCfg("robot")) -> torch.Tensor:
"""Penalize xy-axis base angular velocity using L2-kernel."""
"""Penalize xy-axis base angular velocity using L2 squared kernel."""
# extract the used quantities (to enable type-hinting)
asset: RigidObject = env.scene[asset_cfg.name]
return torch.sum(torch.square(asset.data.root_ang_vel_b[:, :2]), dim=1)


def flat_orientation_l2(env: ManagerBasedRLEnv, asset_cfg: SceneEntityCfg = SceneEntityCfg("robot")) -> torch.Tensor:
"""Penalize non-flat base orientation using L2-kernel.
"""Penalize non-flat base orientation using L2 squared kernel.

This is computed by penalizing the xy-components of the projected gravity vector.
"""
Expand All @@ -100,7 +100,7 @@ def flat_orientation_l2(env: ManagerBasedRLEnv, asset_cfg: SceneEntityCfg = Scen
def base_height_l2(
env: ManagerBasedRLEnv, target_height: float, asset_cfg: SceneEntityCfg = SceneEntityCfg("robot")
) -> torch.Tensor:
"""Penalize asset height from its target using L2-kernel.
"""Penalize asset height from its target using L2 squared kernel.

Note:
Currently, it assumes a flat terrain, i.e. the target height is in the world frame.
Expand All @@ -123,9 +123,9 @@ def body_lin_acc_l2(env: ManagerBasedRLEnv, asset_cfg: SceneEntityCfg = SceneEnt


def joint_torques_l2(env: ManagerBasedRLEnv, asset_cfg: SceneEntityCfg = SceneEntityCfg("robot")) -> torch.Tensor:
"""Penalize joint torques applied on the articulation using L2-kernel.
"""Penalize joint torques applied on the articulation using L2 squared kernel.

NOTE: Only the joints configured in :attr:`asset_cfg.joint_ids` will have their joint torques contribute to the L2 norm.
NOTE: Only the joints configured in :attr:`asset_cfg.joint_ids` will have their joint torques contribute to the term.
"""
# extract the used quantities (to enable type-hinting)
asset: Articulation = env.scene[asset_cfg.name]
Expand All @@ -140,19 +140,19 @@ def joint_vel_l1(env: ManagerBasedRLEnv, asset_cfg: SceneEntityCfg) -> torch.Ten


def joint_vel_l2(env: ManagerBasedRLEnv, asset_cfg: SceneEntityCfg = SceneEntityCfg("robot")) -> torch.Tensor:
"""Penalize joint velocities on the articulation using L1-kernel.
"""Penalize joint velocities on the articulation using L2 squared kernel.

NOTE: Only the joints configured in :attr:`asset_cfg.joint_ids` will have their joint velocities contribute to the L1 norm.
NOTE: Only the joints configured in :attr:`asset_cfg.joint_ids` will have their joint velocities contribute to the term.
"""
# extract the used quantities (to enable type-hinting)
asset: Articulation = env.scene[asset_cfg.name]
return torch.sum(torch.square(asset.data.joint_vel[:, asset_cfg.joint_ids]), dim=1)


def joint_acc_l2(env: ManagerBasedRLEnv, asset_cfg: SceneEntityCfg = SceneEntityCfg("robot")) -> torch.Tensor:
"""Penalize joint accelerations on the articulation using L2-kernel.
"""Penalize joint accelerations on the articulation using L2 squared kernel.

NOTE: Only the joints configured in :attr:`asset_cfg.joint_ids` will have their joint accelerations contribute to the L2 norm.
NOTE: Only the joints configured in :attr:`asset_cfg.joint_ids` will have their joint accelerations contribute to the term.
"""
# extract the used quantities (to enable type-hinting)
asset: Articulation = env.scene[asset_cfg.name]
Expand Down Expand Up @@ -232,12 +232,12 @@ def applied_torque_limits(env: ManagerBasedRLEnv, asset_cfg: SceneEntityCfg = Sc


def action_rate_l2(env: ManagerBasedRLEnv) -> torch.Tensor:
"""Penalize the rate of change of the actions using L2-kernel."""
"""Penalize the rate of change of the actions using L2 squared kernel."""
return torch.sum(torch.square(env.action_manager.action - env.action_manager.prev_action), dim=1)


def action_l2(env: ManagerBasedRLEnv) -> torch.Tensor:
"""Penalize the actions using L2-kernel."""
"""Penalize the actions using L2 squared kernel."""
return torch.sum(torch.square(env.action_manager.action), dim=1)


Expand Down
Loading