unilab.envs.locomotion.go2w.joystick.RewardConfig

class unilab.envs.locomotion.go2w.joystick.RewardConfig[source]

Bases: object

RewardConfig(scales: ‘dict[str, float]’, tracking_sigma: ‘float’, base_height_target: ‘float’, only_positive_rewards: ‘bool’ = False, joint_pos_penalty_stand_still_scale: ‘float’ = 5.0, joint_pos_penalty_velocity_threshold: ‘float’ = 0.5, joint_pos_penalty_command_threshold: ‘float’ = 0.1)

Parameters:

  • scales (dict[str, float])

  • tracking_sigma (float)

  • base_height_target (float)

  • only_positive_rewards (bool)

  • joint_pos_penalty_stand_still_scale (float)

  • joint_pos_penalty_velocity_threshold (float)

  • joint_pos_penalty_command_threshold (float)

Methods

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

Attributes

joint_pos_penalty_command_threshold

joint_pos_penalty_stand_still_scale

joint_pos_penalty_velocity_threshold

only_positive_rewards

scales

tracking_sigma

base_height_target

scales: dict[str, float]
tracking_sigma: float
base_height_target: float
only_positive_rewards: bool = False
joint_pos_penalty_stand_still_scale: float = 5.0
joint_pos_penalty_velocity_threshold: float = 0.5
joint_pos_penalty_command_threshold: float = 0.1
__init__(scales, tracking_sigma, base_height_target, only_positive_rewards=False, joint_pos_penalty_stand_still_scale=5.0, joint_pos_penalty_velocity_threshold=0.5, joint_pos_penalty_command_threshold=0.1)
Parameters:

  • scales (dict[str, float])

  • tracking_sigma (float)

  • base_height_target (float)

  • only_positive_rewards (bool)

  • joint_pos_penalty_stand_still_scale (float)

  • joint_pos_penalty_velocity_threshold (float)

  • joint_pos_penalty_command_threshold (float)