gfn.containers.replay_buffer_manager
====================================

.. py:module:: gfn.containers.replay_buffer_manager


Classes
-------

.. autoapisummary::

   gfn.containers.replay_buffer_manager.ReplayBufferManager


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

.. py:class:: ReplayBufferManager(env, rank, num_training_ranks, scoring_function = None, diverse_replay_buffer = False, capacity = 10000, remote_manager_rank = None)

   .. py:method:: _compute_metadata()
      :abstractmethod:



   .. py:method:: _recv_object()


   .. py:attribute:: capacity
      :value: 10000



   .. py:method:: default_scoring_function(obj)

      Default score function if none provided, placeholder.



   .. py:attribute:: diverse_replay_buffer
      :value: False



   .. py:attribute:: exit_counter
      :value: 0



   .. py:method:: get_metadata(manager_rank)
      :staticmethod:


      Sends a get metadata signal to the replay buffer manager.



   .. py:attribute:: is_running
      :value: True



   .. py:attribute:: num_training_ranks


   .. py:attribute:: rank


   .. py:attribute:: remote_manager_rank
      :value: None



   .. py:method:: run()

      Runs on remote buffer manager ranks. Waits for training data, computes reward, sends back.



   .. py:attribute:: scoring_function


   .. py:method:: send_termination_signal(manager_rank)
      :staticmethod:


      Sends a termination signal to the replay buffer manager.