def test_get_mean_and_standard_deviation_difference_results():
"""Tests that get_mean_and_standard_deviation_difference_results method produces correct output"""
results = [[1.0, 2.0, 3.0], [5.0, -33.0, 55.0], [2.5, 2.5, 2.5]]
mean_results = [
np.mean([1.0, 5.0, 2.5]),
np.mean([2.0, -33.0, 2.5]),
np.mean([3.0, 55.0, 2.5])
]
std_results = [
np.std([1.0, 5.0, 2.5]),
np.std([2.0, -33.0, 2.5]),
np.std([3.0, 55.0, 2.5])
]
mean_minus_1_std = [
mean - std_val for mean, std_val in zip(mean_results, std_results)
]
mean_plus_1_std = [
mean + std_val for mean, std_val in zip(mean_results, std_results)
]
config = Config()
config.standard_deviation_results = 1.0
trainer = Trainer(config, [])
mean_minus_x_std_guess, mean_results_guess, mean_plus_x_std_guess = trainer.get_mean_and_standard_deviation_difference_results(
results)
assert mean_results == mean_results_guess
assert mean_minus_1_std == mean_minus_x_std_guess
assert mean_plus_1_std == mean_plus_x_std_guess
config.standard_deviation_results = 3.0
trainer = Trainer(config, [])
mean_minus_x_std_guess, mean_results_guess, mean_plus_x_std_guess = trainer.get_mean_and_standard_deviation_difference_results(
results)
mean_plus_3_std = [
mean + 3.0 * std_val
for mean, std_val in zip(mean_results, std_results)
]
mean_minus_3_std = [
mean - 3.0 * std_val
for mean, std_val in zip(mean_results, std_results)
]
assert mean_results == mean_results_guess
assert mean_minus_3_std == mean_minus_x_std_guess
assert mean_plus_3_std == mean_plus_x_std_guess
from drl.agents.hierarchical_agents.HRL.HRL import HRL
from drl.agents.Trainer import Trainer
from drl.utilities.data_structures.Config import Config
config = Config()
config.environment = gym.make("Taxi-v2")
config.seed = 1
config.env_parameters = {}
config.num_episodes_to_run = 2000
config.file_to_save_data_results = None
config.file_to_save_results_graph = None
config.show_solution_score = False
config.visualise_individual_results = False
config.visualise_overall_agent_results = True
config.standard_deviation_results = 1.0
config.runs_per_agent = 3
config.use_GPU = False
config.overwrite_existing_results_file = False
config.randomise_random_seed = True
config.save_model = False
linear_hidden_units = [32, 32]
learning_rate = 0.01
buffer_size = 100000
batch_size = 256
batch_norm = False
embedding_dimensionality = 10
gradient_clipping_norm = 5
update_every_n_steps = 1
learning_iterations = 1