def test_fit_unnormalized(self):
box_env_spec = GarageEnv(DummyBoxEnv(obs_dim=(2, ))).spec
gmb = GaussianMLPBaseline(env_spec=box_env_spec,
subsample_factor=0.9,
normalize_inputs=False,
normalize_outputs=False)
train_paths, _, _, paths, expected = get_train_test_data()
for _ in range(150):
gmb.fit(train_paths)
prediction = gmb.predict(paths)
assert np.allclose(prediction, expected, rtol=0, atol=0.1)
x_mean = self.sess.run(gmb._networks['default'].x_mean)
x_mean_expected = np.zeros_like(x_mean)
x_std = self.sess.run(gmb._networks['default'].x_std)
x_std_expected = np.ones_like(x_std)
assert np.array_equal(x_mean, x_mean_expected)
assert np.array_equal(x_std, x_std_expected)
y_mean = self.sess.run(gmb._networks['default'].y_mean)
y_mean_expected = np.zeros_like(y_mean)
y_std = self.sess.run(gmb._networks['default'].y_std)
y_std_expected = np.ones_like(y_std)
assert np.allclose(y_mean, y_mean_expected)
assert np.allclose(y_std, y_std_expected)
def test_fit_normalized(self):
box_env_spec = GarageEnv(DummyBoxEnv(obs_dim=(2, ))).spec
gmb = GaussianMLPBaseline(env_spec=box_env_spec)
(train_paths, observations, returns, paths,
expected) = get_train_test_data()
for _ in range(150):
gmb.fit(train_paths)
prediction = gmb.predict(paths)
assert np.allclose(prediction, expected, rtol=0, atol=0.1)
x_mean = self.sess.run(gmb._networks['default'].x_mean)
x_mean_expected = np.mean(observations, axis=0, keepdims=True)
x_std = self.sess.run(gmb._networks['default'].x_std)
x_std_expected = np.std(observations, axis=0, keepdims=True)
assert np.allclose(x_mean, x_mean_expected)
assert np.allclose(x_std, x_std_expected)
y_mean = self.sess.run(gmb._networks['default'].y_mean)
y_mean_expected = np.mean(returns, axis=0, keepdims=True)
y_std = self.sess.run(gmb._networks['default'].y_std)
y_std_expected = np.std(returns, axis=0, keepdims=True)
assert np.allclose(y_mean, y_mean_expected)
assert np.allclose(y_std, y_std_expected)
def test_unflattened_input(self):
env = GymEnv(DummyBoxEnv(obs_dim=(2, 2)))
gmb = GaussianMLPBaseline(env_spec=env.spec)
env.reset()
es = env.step(1)
obs, rewards = es.observation, es.reward
train_paths = [{'observations': [obs], 'returns': [rewards]}]
gmb.fit(train_paths)
paths = {'observations': [obs]}
prediction = gmb.predict(paths)
assert np.allclose(0., prediction)
def test_fit_smaller_subsample_factor(self):
box_env_spec = GarageEnv(DummyBoxEnv(obs_dim=(2, ))).spec
gmb = GaussianMLPBaseline(env_spec=box_env_spec, subsample_factor=0.9)
train_paths, _, _, paths, expected = get_train_test_data()
for _ in range(150):
gmb.fit(train_paths)
prediction = gmb.predict(paths)
assert np.allclose(prediction, expected, rtol=0, atol=0.1)
def test_fit_without_trusted_region(self):
box_env_spec = GarageEnv(DummyBoxEnv(obs_dim=(2, ))).spec
gmb = GaussianMLPBaseline(env_spec=box_env_spec,
use_trust_region=False)
train_paths, _, _, paths, expected = get_train_test_data()
for _ in range(150):
gmb.fit(train_paths)
prediction = gmb.predict(paths)
assert np.allclose(prediction, expected, rtol=0, atol=0.1)
def test_fit(self, obs_dim):
box_env = TfEnv(DummyBoxEnv(obs_dim=obs_dim))
with mock.patch(('garage.tf.baselines.'
'gaussian_mlp_baseline.'
'GaussianMLPRegressor'),
new=SimpleGaussianMLPRegressor):
gmb = GaussianMLPBaseline(env_spec=box_env.spec)
paths = [{
'observations': [np.full(obs_dim, 1)],
'returns': [1]
}, {
'observations': [np.full(obs_dim, 2)],
'returns': [2]
}]
gmb.fit(paths)
obs = {'observations': [np.full(obs_dim, 1), np.full(obs_dim, 2)]}
prediction = gmb.predict(obs)
assert np.array_equal(prediction, [1, 2])
