StochasticBanditEnv
===================

.. currentmodule:: statrl.settings.bandits.stochastic.anytime.environment

.. autoclass:: StochasticBanditEnv
   :members:

   
   
   .. rubric:: Methods

   .. autosummary::
   
      ~StochasticBanditEnv.__init__
      ~StochasticBanditEnv.close
      ~StochasticBanditEnv.expected_reward
      ~StochasticBanditEnv.get_wrapper_attr
      ~StochasticBanditEnv.has_wrapper_attr
      ~StochasticBanditEnv.render
      ~StochasticBanditEnv.reset
      ~StochasticBanditEnv.set_wrapper_attr
      ~StochasticBanditEnv.step
   
   

   
   
   .. rubric:: Attributes

   .. autosummary::
   
      ~StochasticBanditEnv.means
      ~StochasticBanditEnv.metadata
      ~StochasticBanditEnv.np_random
      ~StochasticBanditEnv.np_random_seed
      ~StochasticBanditEnv.number_arms
      ~StochasticBanditEnv.optimal_arm
      ~StochasticBanditEnv.optimal_mean
      ~StochasticBanditEnv.render_mode
      ~StochasticBanditEnv.spec
      ~StochasticBanditEnv.unwrapped
      ~StochasticBanditEnv.action_space
      ~StochasticBanditEnv.observation_space