unilab.envs.mdp.actions.actions.JointEffortAction

class unilab.envs.mdp.actions.actions.JointEffortAction[source]

Bases: BaseAction

Control joints via effort targets.

Parameters:

Methods

__init__(cfg, env)

apply_actions()

process_actions(actions)

publish_validation_verdict()

Fail closed on the latest action-slice finite verdict.

reset([env_ids])

Zero the raw actions of the selected envs.

validate_actions()

Publish the manager-owned raw-action finite verdict.

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_ids

target_names

uses_tensor_state_packet

Whether apply_actions consumes the current packed tensor state packet.

cfg

apply_actions()[source]
Return type:

None

__call__(*args, **kwargs)

Returns the value of the term required by the manager.

Return type:

Any

__init__(cfg, env)
Parameters:
property action_dim: int
property name: str
property num_envs: int
property offset: float | Tensor
process_actions(actions)
Parameters:

actions (Tensor)

Return type:

None

property processed_action: Tensor
publish_validation_verdict()

Fail closed on the latest action-slice finite verdict.

Return type:

None

property raw_action: Tensor
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.

reset(env_ids=None)

Zero the raw actions of the selected envs.

Parameters:

env_ids (Tensor | None)

Return type:

None

property scale: float | Tensor
property target_ids: tuple[int, ...]
property target_names: list[str]
uses_tensor_state_packet: ClassVar[bool] = False

Whether apply_actions consumes the current packed tensor state packet.

validate_actions()

Publish the manager-owned raw-action finite verdict.

Return type:

None

cfg: BaseActionCfg