rcognita.scenarios.EpisodicScenarioREINFORCE

class rcognita.scenarios.EpisodicScenarioREINFORCE(*args, learning_rate=0.001, is_fixed_actor_weights=False, is_plot_critic=False, **kwargs)

__init__(*args, learning_rate=0.001, is_fixed_actor_weights=False, is_plot_critic=False, **kwargs)

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__(*args[, learning_rate, …])	Initialize self.
get_mean(array)
get_mean_REINFORCE_gradient()
iteration_update()
memorize()	This is a decorator for a simulator step method.
perform_post_step_operations()
plot_critic()
reload_pipeline()
reset_episode()
reset_iteration()
reset_simulation()
run()
step()
store_REINFORCE_objective_gradient()
update_outcome(observation, action, delta)	Sample-to-sample accumulated (summed up or integrated) stage objective.
update_time_from_cache()

Attributes

cache