def test_logger(tmpdir):
logger_1 = Logger('test', seed=1, results_dir=tmpdir)
logger_2 = Logger('test', seed=2, results_dir=tmpdir)
for i in range(3):
logger_1.log_numpy(a=i, b=2 * i + 1)
logger_2.log_numpy(a=2 * i + 1, b=i)
a_1 = np.load(str(tmpdir / 'test' / 'a-1.npy'))
a_2 = np.load(str(tmpdir / 'test' / 'a-2.npy'))
b_1 = np.load(str(tmpdir / 'test' / 'b-1.npy'))
b_2 = np.load(str(tmpdir / 'test' / 'b-2.npy'))
assert np.array_equal(a_1, np.arange(3))
assert np.array_equal(b_2, np.arange(3))
assert np.array_equal(a_1, b_2)
assert np.array_equal(b_1, a_2)
logger_1_bis = Logger('test', append=True, seed=1, results_dir=tmpdir)
logger_1_bis.log_numpy(a=3, b=7)
a_1 = np.load(str(tmpdir / 'test' / 'a-1.npy'))
b_2 = np.load(str(tmpdir / 'test' / 'b-2.npy'))
assert np.array_equal(a_1, np.arange(4))
assert np.array_equal(b_2, np.arange(3))
logger.epoch_info(0, J=J, R=R, any_label='any value')
for i in trange(epochs):
# Here some learning
core.learn(n_steps=100, n_steps_per_fit=1)
sleep(0.5)
dataset = core.evaluate(n_steps=100)
sleep(0.5)
J = np.mean(compute_J(dataset, mdp.info.gamma)) # Discounted returns
R = np.mean(compute_J(dataset)) # Undiscounted returns
# Here logging epoch results to the console
logger.epoch_info(i+1, J=J, R=R)
# Logging the data in J.npy and E.npy
logger.log_numpy(J=J, R=R)
# Logging the best agent according to the best J
logger.log_best_agent(agent, J)
# Logging the last agent
logger.log_agent(agent)
# Log the last dataset
logger.log_dataset(dataset)
logger.info('Experiment terminated')
# Loggers can also continue from previous logs results
del logger # Delete previous logger
new_logger = Logger('tutorial', results_dir='/tmp/logs',
