def test_bcmodule_rnn_update(is_sac):
mock_specs = mb.create_mock_3dball_behavior_specs()
bc_settings = BehavioralCloningSettings(demo_path=CONTINUOUS_DEMO_PATH)
bc_module = create_bc_module(mock_specs, bc_settings, True, is_sac)
stats = bc_module.update()
for _, item in stats.items():
assert isinstance(item, np.float32)
def test_bcmodule_update(is_sac):
mock_specs = mb.create_mock_3dball_behavior_specs()
bc_settings = BehavioralCloningSettings(
demo_path=os.path.dirname(os.path.abspath(__file__)) + "/" +
"test.demo")
bc_module = create_bc_module(mock_specs, bc_settings, False, is_sac)
stats = bc_module.update()
assert_stats_are_float(stats)
def test_bcmodule_rnn_update(is_sac):
mock_specs = mb.create_mock_3dball_behavior_specs()
bc_settings = BehavioralCloningSettings(
demo_path=os.path.dirname(os.path.abspath(__file__)) + "/" +
"test.demo")
bc_module = create_bc_module(mock_specs, bc_settings, True, is_sac)
stats = bc_module.update()
for _, item in stats.items():
assert isinstance(item, np.float32)
def test_bcmodule_constant_lr_update(is_sac):
mock_specs = mb.create_mock_3dball_behavior_specs()
bc_settings = BehavioralCloningSettings(demo_path=CONTINUOUS_DEMO_PATH, steps=0)
bc_module = create_bc_module(mock_specs, bc_settings, False, is_sac)
stats = bc_module.update()
for _, item in stats.items():
assert isinstance(item, np.float32)
old_learning_rate = bc_module.current_lr
_ = bc_module.update()
assert old_learning_rate == bc_module.current_lr
def test_bcmodule_linear_lr_update(is_sac):
mock_specs = mb.create_mock_3dball_behavior_specs()
bc_settings = BehavioralCloningSettings(
demo_path=os.path.dirname(os.path.abspath(__file__)) + "/" + "test.demo",
steps=100,
)
bc_module = create_bc_module(mock_specs, bc_settings, False, is_sac)
# Should decay by 10/100 * 0.0003 = 0.00003
bc_module.policy.get_current_step = MagicMock(return_value=10)
old_learning_rate = bc_module.current_lr
_ = bc_module.update()
assert old_learning_rate - 0.00003 == pytest.approx(bc_module.current_lr, abs=0.01)
def test_bcmodule_defaults():
# See if default values match
mock_specs = mb.create_mock_3dball_behavior_specs()
bc_settings = BehavioralCloningSettings(demo_path=CONTINUOUS_DEMO_PATH)
bc_module = create_bc_module(mock_specs, bc_settings, False, False)
assert bc_module.num_epoch == 3
assert bc_module.batch_size == TrainerSettings().hyperparameters.batch_size
# Assign strange values and see if it overrides properly
bc_settings = BehavioralCloningSettings(
demo_path=CONTINUOUS_DEMO_PATH, num_epoch=100, batch_size=10000
)
bc_module = create_bc_module(mock_specs, bc_settings, False, False)
assert bc_module.num_epoch == 100
assert bc_module.batch_size == 10000
def test_bcmodule_constant_lr_update(is_sac):
mock_specs = mb.create_mock_3dball_behavior_specs()
bc_settings = BehavioralCloningSettings(
demo_path=os.path.dirname(os.path.abspath(__file__)) + "/" + "test.demo",
steps=0,
)
bc_module = create_bc_module(mock_specs, bc_settings, False, is_sac)
stats = bc_module.update()
for _, item in stats.items():
assert isinstance(item, np.float32)
old_learning_rate = bc_module.current_lr
_ = bc_module.update()
assert old_learning_rate == bc_module.current_lr
def test_bcmodule_defaults():
# See if default values match
mock_specs = mb.create_mock_3dball_behavior_specs()
bc_settings = BehavioralCloningSettings(
demo_path=os.path.dirname(os.path.abspath(__file__)) + "/" + "test.demo"
)
bc_module = create_bc_module(mock_specs, bc_settings, False, False)
assert bc_module.num_epoch == 3
assert bc_module.batch_size == TrainerSettings().hyperparameters.batch_size
# Assign strange values and see if it overrides properly
bc_settings = BehavioralCloningSettings(
demo_path=os.path.dirname(os.path.abspath(__file__)) + "/" + "test.demo",
num_epoch=100,
batch_size=10000,
)
bc_module = create_bc_module(mock_specs, bc_settings, False, False)
assert bc_module.num_epoch == 100
assert bc_module.batch_size == 10000
import tempfile
from mlagents_envs.communicator_objects.demonstration_meta_pb2 import (
DemonstrationMetaProto, )
from mlagents.trainers.tests.mock_brain import (
create_mock_3dball_behavior_specs,
setup_test_behavior_specs,
)
from mlagents.trainers.demo_loader import (
load_demonstration,
demo_to_buffer,
get_demo_files,
write_delimited,
)
BEHAVIOR_SPEC = create_mock_3dball_behavior_specs()
def test_load_demo():
path_prefix = os.path.dirname(os.path.abspath(__file__))
behavior_spec, pair_infos, total_expected = load_demonstration(
path_prefix + "/test.demo")
assert np.sum(behavior_spec.observation_shapes[0]) == 8
assert len(pair_infos) == total_expected
_, demo_buffer = demo_to_buffer(path_prefix + "/test.demo", 1,
BEHAVIOR_SPEC)
assert (len(demo_buffer["continuous_action"]) == total_expected - 1
or len(demo_buffer["discrete_action"]) == total_expected - 1)
