mpcrl.LearningAgent
===================

.. currentmodule:: mpcrl

.. autoclass:: LearningAgent
   :members:
   :show-inheritance:
   :undoc-members:
   :inherited-members:

   
   
   .. rubric:: Methods

   .. autosummary::
      :template: function.rst
   
      ~LearningAgent.action_value
      ~LearningAgent.evaluate
      ~LearningAgent.is_wrapped
      ~LearningAgent.on_env_step
      ~LearningAgent.on_episode_end
      ~LearningAgent.on_episode_start
      ~LearningAgent.on_mpc_failure
      ~LearningAgent.on_timestep_end
      ~LearningAgent.on_training_end
      ~LearningAgent.on_training_start
      ~LearningAgent.on_update
      ~LearningAgent.on_update_failure
      ~LearningAgent.on_validation_end
      ~LearningAgent.on_validation_start
      ~LearningAgent.reset
      ~LearningAgent.state_value
      ~LearningAgent.store_experience
      ~LearningAgent.train
      ~LearningAgent.train_offpolicy
      ~LearningAgent.train_one_episode
      ~LearningAgent.train_one_rollout
      ~LearningAgent.update
   
   

   
   
   .. rubric:: Attributes

   .. autosummary::
   
      ~LearningAgent.Q
      ~LearningAgent.V
      ~LearningAgent.cost_perturbation_method
      ~LearningAgent.cost_perturbation_parameter
      ~LearningAgent.experience
      ~LearningAgent.exploration
      ~LearningAgent.fixed_parameters
      ~LearningAgent.init_action_constraint
      ~LearningAgent.init_action_parameter
      ~LearningAgent.learnable_parameters
      ~LearningAgent.unwrapped
      ~LearningAgent.update_strategy
      ~LearningAgent.warmstart
   
   

.. minigallery:: mpcrl.LearningAgent
    :add-heading: