robopal.envs.manipulation_tasks.demo_pick_place module¶
- class robopal.envs.manipulation_tasks.demo_pick_place.PickAndPlaceEnv(robot='PandaPickAndPlace', render_mode='human', control_freq=20, is_show_camera_in_cv=False, controller='CARTIK', action_type='velocity', is_render_camera_offscreen=False, camera_in_render='frontview', camera_in_window='free', is_randomize_end=False, is_randomize_object=True, is_randomize_goal=False)[源代码]¶
-
- action_dim: np.ndarray¶
- compute_rewards(achieved_goal: ndarray = array([0., 0., 0.]), desired_goal: ndarray = array([0., 0., 0.]), info: dict = None, **kwargs)[源代码]¶
Sparse Reward: the returned reward can have two values: -1 if the block hasn’t reached its final target position, and 0 if the block is in the final target position (the block is considered to have reached the goal if the Euclidean distance between both is lower than 0.05 m).
- controller: BaseController¶
- mj_data: mujoco.MjData¶
- mj_model: mujoco.MjModel¶
- name = 'PickAndPlace-v1'¶
- obs_dim: np.ndarray¶