Language

unilab.envs.locomotion.go2.handstand.RewardConfig¶

class unilab.envs.locomotion.go2.handstand.RewardConfig[source]¶

Bases: object

RewardConfig(scales: ‘dict[str, float]’, tracking_sigma: ‘float’, base_height_target: ‘float’, target_foot_height: ‘float’ = 0.1, knee_height_target: ‘float’ = 0.08)

Parameters:

scales (dict[str, float])
tracking_sigma (float)
base_height_target (float)
target_foot_height (float)
knee_height_target (float)

Methods

__init__(scales, tracking_sigma, ...[, ...])

Attributes

`knee_height_target`
`target_foot_height`
`scales`
`tracking_sigma`
`base_height_target`

scales: dict[str, float]¶

tracking_sigma: float¶

base_height_target: float¶

target_foot_height: float = 0.1¶

knee_height_target: float = 0.08¶

__init__(scales, tracking_sigma, base_height_target, target_foot_height=0.1, knee_height_target=0.08)¶

Parameters:

scales (dict[str, float])
tracking_sigma (float)
base_height_target (float)
target_foot_height (float)
knee_height_target (float)