def run(self) -> None:
"""
Runs all episodes with pivotal parameters.
Visualizes one round at the end.
"""
self.__ANET.save('0.h5') # Save the untrained ANET prior to episode 1
for episode in range(1, self.__episodes + 1):
print('\nEpisode:', episode)
self.__run_one_episode()
if episode % self.__caching_interval == 0:
# Save ANET for later use in tournament play.
self.__ANET.save(str(episode) + '.h5')
Visualize.plot_loss(self.__ANET.loss_history)
Visualize.plot_epsilon(self.__ANET.epsilon_history)
if parameters.VISUALIZE_GAMES:
print('Showing one episode with the greedy strategy.')
ReinforcementLearner.run_one_game(self.__ANET, self.__ANET, True)
def plot_training_data(self) -> None:
Visualize.plot_epsilon(self.__epsilon_history)
Visualize.plot_td_error(self.__td_error_history)