local_dm_control_suite/humanoid.py [193:211]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                                bounds=(0.9, float('inf')), sigmoid='linear',
                                margin=1.9, value_at_margin=0)
    stand_reward = standing * upright
    small_control = rewards.tolerance(physics.control(), margin=1,
                                      value_at_margin=0,
                                      sigmoid='quadratic').mean()
    small_control = (4 + small_control) / 5
    if self._move_speed == 0:
      horizontal_velocity = physics.center_of_mass_velocity()[[0, 1]]
      dont_move = rewards.tolerance(horizontal_velocity, margin=2).mean()
      return small_control * stand_reward * dont_move
    else:
      com_velocity = np.linalg.norm(physics.center_of_mass_velocity()[[0, 1]])
      move = rewards.tolerance(com_velocity,
                               bounds=(self._move_speed, float('inf')),
                               margin=self._move_speed, value_at_margin=0,
                               sigmoid='linear')
      move = (5*move + 1) / 6
      return small_control * stand_reward * move
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



local_dm_control_suite/humanoid_CMU.py [161:179]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                                bounds=(0.9, float('inf')), sigmoid='linear',
                                margin=1.9, value_at_margin=0)
    stand_reward = standing * upright
    small_control = rewards.tolerance(physics.control(), margin=1,
                                      value_at_margin=0,
                                      sigmoid='quadratic').mean()
    small_control = (4 + small_control) / 5
    if self._move_speed == 0:
      horizontal_velocity = physics.center_of_mass_velocity()[[0, 1]]
      dont_move = rewards.tolerance(horizontal_velocity, margin=2).mean()
      return small_control * stand_reward * dont_move
    else:
      com_velocity = np.linalg.norm(physics.center_of_mass_velocity()[[0, 1]])
      move = rewards.tolerance(com_velocity,
                               bounds=(self._move_speed, float('inf')),
                               margin=self._move_speed, value_at_margin=0,
                               sigmoid='linear')
      move = (5*move + 1) / 6
      return small_control * stand_reward * move
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -