DiscreteMDP
===========

.. currentmodule:: statrl.settings.markovdecisionprocess.discrete_nostructure.environment

.. autoclass:: DiscreteMDP
   :members:

   
   
   .. rubric:: Methods

   .. autosummary::
   
      ~DiscreteMDP.__init__
      ~DiscreteMDP.change_rendermode
      ~DiscreteMDP.close
      ~DiscreteMDP.expected_reward
      ~DiscreteMDP.getMeanReward
      ~DiscreteMDP.getTransition
      ~DiscreteMDP.get_wrapper_attr
      ~DiscreteMDP.has_wrapper_attr
      ~DiscreteMDP.render
      ~DiscreteMDP.reset
      ~DiscreteMDP.seed
      ~DiscreteMDP.set_wrapper_attr
      ~DiscreteMDP.step
   
   

   
   
   .. rubric:: Attributes

   .. autosummary::
   
      ~DiscreteMDP.metadata
      ~DiscreteMDP.np_random
      ~DiscreteMDP.np_random_seed
      ~DiscreteMDP.render_mode
      ~DiscreteMDP.spec
      ~DiscreteMDP.unwrapped
      ~DiscreteMDP.action_space
      ~DiscreteMDP.observation_space