def load(noise_scale, seed):
"""Load a bandit_noise experiment with the prescribed settings."""
env = wrappers.RewardNoise(env=bandit.SimpleBandit(seed=seed),
noise_scale=noise_scale,
seed=seed)
env.bsuite_num_episodes = sweep.NUM_EPISODES
return env
def load(mean_rewards=None, seed=None):
"""Load a bandit_noise experiment with the prescribed settings."""
env = wrappers.RewardNoise(env=bandit.SimpleBandit(rewards=mean_rewards,
seed=seed),
bernoulli=True,
seed=seed)
env.bsuite_num_episodes = sweep.NUM_EPISODES
return env
def make_object_under_test(self):
return bandit.SimpleBandit(5)
def make_object_under_test(self):
return bandit.SimpleBandit(rewards=[0.1, 0.3, 0.7], seed=5)