@pytest.mark.parametrize("critic_optim_factory", [AdamFactory()])
@pytest.mark.parametrize("temp_optim_factory", [AdamFactory()])
@pytest.mark.parametrize("alpha_optim_factory", [AdamFactory()])
@pytest.mark.parametrize("encoder_factory", [DefaultEncoderFactory()])
@pytest.mark.parametrize("q_func_factory", ["mean", "qr", "iqn", "fqf"])
@pytest.mark.parametrize("gamma", [0.99])
@pytest.mark.parametrize("tau", [0.05])
@pytest.mark.parametrize("n_critics", [2])
@pytest.mark.parametrize("bootstrap", [False])
@pytest.mark.parametrize("share_encoder", [False, True])
@pytest.mark.parametrize("initial_temperature", [1.0])
@pytest.mark.parametrize("initial_alpha", [5.0])
@pytest.mark.parametrize("alpha_threshold", [10.0])
@pytest.mark.parametrize("n_action_samples", [10])
@pytest.mark.parametrize("soft_q_backup", [True])
@pytest.mark.parametrize("scaler", [None, DummyScaler()])
@pytest.mark.parametrize("action_scaler", [None, DummyActionScaler()])
@pytest.mark.parametrize("augmentation", [DrQPipeline()])
def test_cql_impl(
observation_shape,
action_size,
actor_learning_rate,
critic_learning_rate,
temp_learning_rate,
alpha_learning_rate,
actor_optim_factory,
critic_optim_factory,
temp_optim_factory,
alpha_optim_factory,
encoder_factory,
q_func_factory,
@pytest.mark.parametrize('alpha_learning_rate', [1e-3])
@pytest.mark.parametrize('gamma', [0.99])
@pytest.mark.parametrize('tau', [0.05])
@pytest.mark.parametrize('n_critics', [2])
@pytest.mark.parametrize('bootstrap', [False])
@pytest.mark.parametrize('share_encoder', [False, True])
@pytest.mark.parametrize('initial_temperature', [1.0])
@pytest.mark.parametrize('initial_alpha', [1.0])
@pytest.mark.parametrize('alpha_threshold', [0.05])
@pytest.mark.parametrize('lam', [0.75])
@pytest.mark.parametrize('n_action_samples', [4])
@pytest.mark.parametrize('mmd_sigma', [20.0])
@pytest.mark.parametrize('eps', [1e-8])
@pytest.mark.parametrize('use_batch_norm', [True, False])
@pytest.mark.parametrize('q_func_type', ['mean', 'qr', 'iqn', 'fqf'])
@pytest.mark.parametrize('scaler', [None, DummyScaler()])
@pytest.mark.parametrize('augmentation', [AugmentationPipeline()])
@pytest.mark.parametrize('n_augmentations', [1])
@pytest.mark.parametrize('encoder_params', [{}])
def test_bear_impl(observation_shape, action_size, actor_learning_rate,
critic_learning_rate, imitator_learning_rate,
temp_learning_rate, alpha_learning_rate, gamma, tau,
n_critics, bootstrap, share_encoder, initial_temperature,
initial_alpha, alpha_threshold, lam, n_action_samples,
mmd_sigma, eps, use_batch_norm, q_func_type, scaler,
augmentation, n_augmentations, encoder_params):
impl = BEARImpl(observation_shape,
action_size,
actor_learning_rate,
critic_learning_rate,
imitator_learning_rate,