def test_clip(self):
obs_spec = array_spec.BoundedArraySpec((2, 3), np.int32, -10, 10)
action_spec = array_spec.BoundedArraySpec((2,), np.float32, [-1, 0], 1)
def mock_step(_, action):
return action
with mock.patch.object(
random_py_environment.RandomPyEnvironment,
'_step',
side_effect=mock_step,
autospec=True,
):
env = random_py_environment.RandomPyEnvironment(
obs_spec, action_spec=action_spec, auto_reset=False)
env = wrappers.ActionClipWrapper(env)
env.reset()
# actions within bounds, use NumPy action
action = env.step(np.array([0, 0]))
np.testing.assert_array_almost_equal([0.0, 0.0], action)
# action 1 outside bounds, use list action
action = env.step([-4, 0])
np.testing.assert_array_almost_equal([-1.0, 0.0], action)
# action 2 outside bounds, use NumPy action
action = env.step(np.array([0, -4]))
np.testing.assert_array_almost_equal([0.0, 0.0], action)
# actions outside bounds, use list action
action = env.step([4, 4])
action = env.step(np.array([4, 4]))
np.testing.assert_array_almost_equal([1.0, 1.0], action)
def test_nested(self):
obs_spec = array_spec.BoundedArraySpec((2, 3), np.int32, -10, 10)
action_spec = [
array_spec.BoundedArraySpec((2,), np.float32, -1, 1), [
array_spec.BoundedArraySpec((2,), np.float32, -2, 2),
array_spec.BoundedArraySpec((2,), np.float32, -3, 3)
]
]
def mock_step(_, action):
return action
with mock.patch.object(
random_py_environment.RandomPyEnvironment,
'step',
side_effect=mock_step,
autospec=True,
):
env = random_py_environment.RandomPyEnvironment(
obs_spec, action_spec=action_spec)
env = wrappers.ActionClipWrapper(env)
# use NumPy action
action = [np.array([10, -10]), [np.array([10, -10]), np.array([10, -10])]]
action = env.step(action)
np.testing.assert_array_almost_equal([1, -1], action[0])
np.testing.assert_array_almost_equal([2, -2], action[1][0])
np.testing.assert_array_almost_equal([3, -3], action[1][1])
# use list action
action = [[10, -10], [[10, -10], [10, -10]]]
action = env.step(action)
np.testing.assert_array_almost_equal([1, -1], action[0])
np.testing.assert_array_almost_equal([2, -2], action[1][0])
np.testing.assert_array_almost_equal([3, -3], action[1][1])
