def test_obs_not_image(self):
env = self.env
with mock.patch(('metarl.tf.models.'
'categorical_cnn_model.CNNModel._build'),
autospec=True,
side_effect=CNNModel._build) as build:
qf = DiscreteCNNQFunction(env_spec=env.spec,
filters=((5, (3, 3)), ),
strides=(2, ),
dueling=False)
normalized_obs = build.call_args_list[0][0][1]
input_ph = qf.input
assert input_ph == normalized_obs
fake_obs = [np.full(env.spec.observation_space.shape, 255)]
assert (self.sess.run(normalized_obs,
feed_dict={input_ph:
fake_obs}) == 255.).all()
obs_dim = env.spec.observation_space.shape
state_input = tf.compat.v1.placeholder(tf.float32,
shape=(None, ) + obs_dim)
qf.get_qval_sym(state_input, name='another')
normalized_obs = build.call_args_list[1][0][1]
fake_obs = [np.full(env.spec.observation_space.shape, 255)]
assert (self.sess.run(normalized_obs,
feed_dict={state_input:
fake_obs}) == 255).all()
def test_get_qval_sym(self, filter_dims, num_filters, strides):
with mock.patch(('metarl.tf.q_functions.'
'discrete_cnn_q_function.CNNModel'),
new=SimpleCNNModel):
with mock.patch(('metarl.tf.q_functions.'
'discrete_cnn_q_function.MLPModel'),
new=SimpleMLPModel):
qf = DiscreteCNNQFunction(env_spec=self.env.spec,
filter_dims=filter_dims,
num_filters=num_filters,
strides=strides,
dueling=False)
output1 = self.sess.run(qf.q_vals, feed_dict={qf.input: [self.obs]})
obs_dim = self.env.observation_space.shape
action_dim = self.env.action_space.n
input_var = tf.compat.v1.placeholder(tf.float32,
shape=(None, ) + obs_dim)
q_vals = qf.get_qval_sym(input_var, 'another')
output2 = self.sess.run(q_vals, feed_dict={input_var: [self.obs]})
expected_output = np.full(action_dim, 0.5)
assert np.array_equal(output1, output2)
assert np.array_equal(output2[0], expected_output)