Language

unilab.tasks.motion_tracking.common.manager_terms.MotionJointPositionAction¶

class unilab.tasks.motion_tracking.common.manager_terms.MotionJointPositionAction[source]¶

Bases: JointPositionAction

Parameters:

cfg (MotionJointPositionActionCfg)
env (ManagerBasedRlEnv)

Methods

`__init__`(cfg, env)
`apply_actions`()
`process_actions`(actions)
`reset`([env_ids])	Resets the manager term.

Attributes

`action_dim`
`name`
`num_envs`
`offset`
`processed_action`
`raw_action`
`requires_substep_state_feedback`	Whether `apply_actions` needs state produced by the previous physics substep.
`scale`
`target`	Most recently applied physical joint target in entity joint order.
`target_ids`
`target_names`
`cfg`

cfg: MotionJointPositionActionCfg¶

__init__(cfg, env)[source]¶

Parameters:

cfg (MotionJointPositionActionCfg)
env (ManagerBasedRlEnv)

property target: ndarray¶: Most recently applied physical joint target in entity joint order.

process_actions(actions)[source]¶

Parameters:: actions (ndarray)
Return type:: None

reset(env_ids=None)[source]¶

Resets the manager term.

Parameters:: env_ids (ndarray | slice | None)
Return type:: None

apply_actions()[source]¶

Return type:: None

__call__(*args, **kwargs)¶

Returns the value of the term required by the manager.

Return type:: Any

property action_dim: int¶

property name: str¶

property num_envs: int¶

property offset: float | ndarray¶

property processed_action: ndarray¶

property raw_action: ndarray¶

requires_substep_state_feedback: ClassVar[bool] = False¶

Whether apply_actions needs state produced by the previous physics substep.

False declares that the generated control is invariant across all physics substeps in one control step, so the env may apply it once before a batched backend step. State-feedback terms must override this declaration with True.

property scale: float | ndarray¶

property target_ids: ndarray¶

property target_names: list[str]¶