def make_monte_carlo_batch(self,
nb_episodes,
render,
policy,
weights_flag=False,
weights=None):
"""
Create a batch of episodes with a given policy
Used in Monte Carlo approaches
:param nb_episodes: the number of episodes in the batch
:param render: whether the episode is displayed or not (True or False)
:param policy: the policy controlling the agent
:param weights_flag
:param weights
:return: the resulting batch of episodes
"""
if weights_flag:
batch = Batch(weights)
else:
batch = Batch()
self.env.set_reward_flag(False)
self.env.set_duration_flag(False)
for e in range(nb_episodes):
episode = self.train_on_one_episode(policy, False, render)
batch.add_episode(episode)
return batch
