def test_cc_bc_model(mock_communicator, mock_launcher):
tf.reset_default_graph()
with tf.Session() as sess:
with tf.variable_scope("FakeGraphScope"):
mock_communicator.return_value = MockCommunicator(
discrete_action=False, visual_inputs=0)
env = UnityEnvironment(' ')
model = BehavioralCloningModel(env.brains["RealFakeBrain"])
init = tf.global_variables_initializer()
sess.run(init)
run_list = [model.sample_action, model.policy]
feed_dict = {model.batch_size: 2,
model.sequence_length: 1,
model.vector_in: np.array([[1, 2, 3, 1, 2, 3],
[3, 4, 5, 3, 4, 5]])}
sess.run(run_list, feed_dict=feed_dict)
env.close()
def test_visual_cc_bc_model():
tf.reset_default_graph()
with tf.Session() as sess:
with tf.variable_scope("FakeGraphScope"):
model = BehavioralCloningModel(
make_brain_parameters(discrete_action=False, visual_inputs=2))
init = tf.global_variables_initializer()
sess.run(init)
run_list = [model.sample_action, model.policy]
feed_dict = {
model.batch_size: 2,
model.sequence_length: 1,
model.vector_in: np.array([[1, 2, 3, 1, 2, 3],
[3, 4, 5, 3, 4, 5]]),
model.visual_in[0]: np.ones([2, 40, 30, 3]),
model.visual_in[1]: np.ones([2, 40, 30, 3]),
}
sess.run(run_list, feed_dict=feed_dict)
def test_dc_bc_model():
tf.reset_default_graph()
with tf.Session() as sess:
with tf.variable_scope("FakeGraphScope"):
model = BehavioralCloningModel(
make_brain_parameters(discrete_action=True, visual_inputs=0))
init = tf.global_variables_initializer()
sess.run(init)
run_list = [model.sample_action, model.action_probs]
feed_dict = {
model.batch_size: 2,
model.dropout_rate: 1.0,
model.sequence_length: 1,
model.vector_in: np.array([[1, 2, 3, 1, 2, 3],
[3, 4, 5, 3, 4, 5]]),
model.action_masks: np.ones([2, 2]),
}
sess.run(run_list, feed_dict=feed_dict)
def __init__(self, seed, brain, trainer_parameters, load):
"""
:param seed: Random seed.
:param brain: Assigned Brain object.
:param trainer_parameters: Defined training parameters.
:param load: Whether a pre-trained model will be loaded or a new one created.
"""
super(BCPolicy, self).__init__(seed, brain, trainer_parameters)
self.last_loss = 0
with self.graph.as_default():
with self.graph.as_default():
self.model = BehavioralCloningModel(
h_size=int(trainer_parameters["hidden_units"]),
lr=float(trainer_parameters["learning_rate"]),
n_layers=int(trainer_parameters["num_layers"]),
m_size=self.m_size,
normalize=False,
use_recurrent=trainer_parameters["use_recurrent"],
brain=brain,
seed=seed,
)
if load:
self._load_graph()
else:
self._initialize_graph()
self.inference_dict = {
"action": self.model.sample_action,
"action_probs": self.model.action_probs
}
self.update_dict = {
"policy_loss": self.model.loss,
"update_batch": self.model.update,
}
if self.use_recurrent:
self.inference_dict["memory_out"] = self.model.memory_out
self.evaluate_rate = 1.0
self.update_rate = 0.5
def test_visual_dc_bc_model(mock_communicator, mock_launcher):
tf.reset_default_graph()
with tf.Session() as sess:
with tf.variable_scope("FakeGraphScope"):
mock_communicator.return_value = MockCommunicator(
discrete_action=True, visual_inputs=2)
env = UnityEnvironment(" ")
model = BehavioralCloningModel(env.brains["RealFakeBrain"])
init = tf.global_variables_initializer()
sess.run(init)
run_list = [model.sample_action, model.action_probs]
feed_dict = {
model.batch_size: 2,
model.dropout_rate: 1.0,
model.sequence_length: 1,
model.vector_in: np.array([[1, 2, 3, 1, 2, 3],
[3, 4, 5, 3, 4, 5]]),
model.visual_in[0]: np.ones([2, 40, 30, 3]),
model.visual_in[1]: np.ones([2, 40, 30, 3]),
model.action_masks: np.ones([2, 2]),
}
sess.run(run_list, feed_dict=feed_dict)
env.close()
def __init__(self, seed, brain, trainer_parameters, load):
"""
:param seed: Random seed.
:param brain: Assigned Brain object.
:param trainer_parameters: Defined training parameters.
:param load: Whether a pre-trained model will be loaded or a new one created.
"""
super(BCPolicy, self).__init__(seed, brain, trainer_parameters)
with self.graph.as_default():
with self.graph.as_default():
self.model = BehavioralCloningModel(
h_size=int(trainer_parameters['hidden_units']),
lr=float(trainer_parameters['learning_rate']),
n_layers=int(trainer_parameters['num_layers']),
m_size=self.m_size,
normalize=False,
use_recurrent=trainer_parameters['use_recurrent'],
brain=brain,
seed=seed)
if load:
self._load_graph()
else:
self._initialize_graph()
self.inference_dict = {'action': self.model.sample_action}
self.update_dict = {
'policy_loss': self.model.loss,
'update_batch': self.model.update
}
if self.use_recurrent:
self.inference_dict['memory_out'] = self.model.memory_out
self.evaluate_rate = 1.0
self.update_rate = 0.5
