unilab.tasks.locomotion.g1.manager_terms.G1WalkRewardPackCfg

class unilab.tasks.locomotion.g1.manager_terms.G1WalkRewardPackCfg[source]

Bases: RewardTermCfg

Fused canonical G1 walk reward family for tensor-resident owners.

Parameters:

Methods

__init__([params, reward_pack_names, ...])

Attributes

command_name

entity_name

feet_phase_sigma

gait_frequency

gait_init_mode

min_forward_speed

pose_weights

reward_pack_names

Ordered outputs when func evaluates multiple terms in one carrier read.

swing_height

tracking_ang_sigma

tracking_lin_sigma

func

The callable that computes this reward term's value.

weight

Weight multiplier for this reward term.

params

Additional keyword arguments passed to func when called.
command_name: str = 'twist'
entity_name: str = 'robot'
tracking_lin_sigma: float = 0.25
tracking_ang_sigma: float = 0.25
gait_frequency: float = 1.5
gait_init_mode: str = 'offset_phase'
swing_height: float = 0.09
feet_phase_sigma: float = 0.04
min_forward_speed: float = 0.0
pose_weights: tuple[float, ...] = (1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0)
__init__(params=<factory>, *, func, weight, reward_pack_names=(), command_name='twist', entity_name='robot', tracking_lin_sigma=0.25, tracking_ang_sigma=0.25, gait_frequency=1.5, gait_init_mode='offset_phase', swing_height=0.09, feet_phase_sigma=0.04, min_forward_speed=0.0, pose_weights=(1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0))
Parameters:
reward_pack_names: tuple[str, ...] = ()

Ordered outputs when func evaluates multiple terms in one carrier read.

func: Any

The callable that computes this reward term’s value.

weight: float

Weight multiplier for this reward term.

params: dict[str, Any]

Additional keyword arguments passed to func when called.