6c91f3853b4426f3f2ac6d98a3aa89a800b8bec3,softlearning/environments/gym/mujoco/humanoid_env.py,HumanoidEnv,__init__,#HumanoidEnv#Any#Any#Any#Any#Any#Any#Any#Any#Any#,21

Before Change

                 exclude_current_positions_from_observation=True):
        self._forward_reward_weight = forward_reward_weight
        self._ctrl_cost_weight = ctrl_cost_weight
        self._contact_cost_weight = contact_cost_weight
        self._contact_cost_range = contact_cost_range
        self._healthy_reward = healthy_reward
        self._terminate_when_unhealthy = terminate_when_unhealthy
        self._healthy_z_range = healthy_z_range

        self._reset_noise_scale = reset_noise_scale

        self._exclude_current_positions_from_observation = (
            exclude_current_positions_from_observation)

        mujoco_env.MujocoEnv.__init__(self, "humanoid.xml", 5)
        utils.EzPickle.__init__(
            self,
            forward_reward_weight=self._forward_reward_weight,
            ctrl_cost_weight=self._ctrl_cost_weight,
            healthy_reward=self._healthy_reward,
            terminate_when_unhealthy=self._terminate_when_unhealthy,
            contact_cost_weight=self._contact_cost_weight,
            contact_cost_range=self._contact_cost_range,
            healthy_z_range=self._healthy_z_range,
            reset_noise_scale=self._reset_noise_scale,
            exclude_current_positions_from_observation=(
                self._exclude_current_positions_from_observation))

    @property
    def healthy_reward(self):
        return float(

After Change

                 healthy_z_range=(1.0, 2.0),
                 reset_noise_scale=1e-2,
                 exclude_current_positions_from_observation=True):
        utils.EzPickle.__init__(**locals())

        self._forward_reward_weight = forward_reward_weight
        self._ctrl_cost_weight = ctrl_cost_weight
        self._contact_cost_weight = contact_cost_weight

Instances