def test_sample_with_critic(self, n_actions):
model = DiscreteUniform(n_actions=n_actions, critic=DummyCritic())
model_states = model.predict(batch_size=1000)
actions = model_states.actions
assert len(actions.shape) == 1
assert len(numpy.unique(actions)) <= n_actions
assert all(actions >= 0)
assert all(actions <= n_actions)
assert "critic_score" in model_states.keys()
assert (model_states.critic_score == 5).all()
states = create_model_states(batch_size=100, model=model)
model_states = model.sample(batch_size=states.n, model_states=states)
actions = model_states.actions
assert len(actions.shape) == 1
assert len(numpy.unique(actions)) <= n_actions
assert all(actions >= 0)
assert all(actions <= n_actions)
assert numpy.allclose(actions, actions.astype(int))
assert "critic_score" in model_states.keys()
assert (model_states.critic_score == 5).all()
def test_sample(self, n_actions):
model = DiscreteUniform(n_actions=n_actions)
model_states = model.predict(batch_size=1000)
actions = model_states.actions
assert len(actions.shape) == 1
assert len(numpy.unique(actions)) <= n_actions
assert all(actions >= 0)
assert all(actions <= n_actions)
assert "critic_score" in model_states.keys()
assert isinstance(model_states.critic_score, numpy.ndarray)
assert (
model_states.critic_score == 1).all(), model_states.critic_score
states = create_model_states(batch_size=100, model=model)
model_states = model.sample(batch_size=states.n, model_states=states)
actions = model_states.actions
assert len(actions.shape) == 1
assert len(numpy.unique(actions)) <= n_actions
assert all(actions >= 0)
assert all(actions <= n_actions)
assert numpy.allclose(actions, actions.astype(int))
assert "critic_score" in model_states.keys()
assert (model_states.critic_score == 1).all()
def test_sample(self, n_actions):
model = DiscreteUniform(n_actions=n_actions)
model_states = model.predict(batch_size=1000)
actions = model_states.actions
assert len(actions.shape) == 1
assert len(judo.unique(actions)) <= n_actions
assert all(actions >= 0)
assert all(actions <= n_actions)
assert "critic_score" in model_states.keys()
assert dtype.is_tensor(model_states.critic_score)
assert (
model_states.critic_score == 1).all(), model_states.critic_score
states = create_model_states(batch_size=100, model=model)
model_states = model.sample(batch_size=states.n, model_states=states)
actions = model_states.actions
assert len(actions.shape) == 1
assert len(judo.unique(actions)) <= n_actions
assert all(actions >= 0)
assert all(actions <= n_actions)
assert judo.allclose(actions, judo.astype(actions, dtype.int))
assert "critic_score" in model_states.keys()
assert (model_states.critic_score == 1).all()