mani_skill.agents.multi_agent
=============================

.. py:module:: mani_skill.agents.multi_agent


Attributes
----------

.. autoapisummary::

   mani_skill.agents.multi_agent.T


Classes
-------

.. autoapisummary::

   mani_skill.agents.multi_agent.MultiAgent


Module Contents
---------------

.. py:class:: MultiAgent(agents)

   Bases: :py:obj:`mani_skill.agents.base_agent.BaseAgent`, :py:obj:`Generic`\ [\ :py:obj:`T`\ ]


   Base class for agents/robots, forming an interface of an articulated robot (SAPIEN's physx.PhysxArticulation).
   Users implementing their own agents/robots should inherit from this class.
   A tutorial on how to build your own agent can be found in :doc:`its tutorial </user_guide/tutorials/custom_robots>`

   :param scene: simulation scene instance.
   :type scene: ManiSkillScene
   :param control_freq: control frequency (Hz).
   :type control_freq: int
   :param control_mode: uid of controller to use
   :type control_mode: str | None
   :param fix_root_link: whether to fix the robot root link
   :type fix_root_link: bool
   :param agent_idx: an index for this agent in a multi-agent task setup If None, the task should be single-agent
   :type agent_idx: str | None
   :param initial_pose: the initial pose of the robot. Important to set for GPU simulation to ensure robot
   :type initial_pose: sapien.Pose | Pose | None
   :param does not collide with other objects in the scene during GPU initialization which occurs before `env._initialize_episode` is called:


   .. py:method:: before_simulation_step()

      Code that runs before each simulation step. By default it calls the controller's before_simulation_step method.



   .. py:method:: get_controller_state()

      Get the state of the controller.



   .. py:method:: get_proprioception()

      Get the proprioceptive state of the agent, default is the qpos and qvel of the robot and any controller state.



   .. py:method:: reset(init_qpos=None)

      Reset the robot to a rest position or a given q-position



   .. py:method:: set_action(action)

      Set the agent's action which is to be executed in the next environment timestep



   .. py:method:: set_control_mode(control_mode = None)

      Set the controller, drive properties, and reset for each agent. If given control mode is None, will set defaults



   .. py:method:: set_controller_state(state)

      Set the state of the controller.



   .. py:attribute:: _sensor_config_agent_map
      :type:  dict[str, int]


   .. py:property:: _sensor_configs
      :type: list[mani_skill.sensors.base_sensor.BaseSensorConfig]


      Returns a list of sensor configs for this agent. It contains the sensor configs of the individual agents.


   .. py:property:: action_space


   .. py:attribute:: agents
      :type:  T


   .. py:attribute:: agents_dict
      :type:  dict[str, mani_skill.agents.base_agent.BaseAgent]


   .. py:property:: control_mode

      Get the currently activated controller uid of each robot


   .. py:property:: controller

      Get currently activated controller.


   .. py:attribute:: scene


   .. py:attribute:: sensor_configs
      :value: []



   .. py:property:: single_action_space


.. py:data:: T