def test_check_array_bounds(self):
obs_spec = array_spec.BoundedArraySpec((2, 3), np.int32, -10, 10)
action_spec = array_spec.BoundedArraySpec((2,), np.float32, [-10, 0], 10)
limits = np.array([2, 5])
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.ActionDiscretizeWrapper(env, limits)
env.reset()
action = env.step([0, 0])
np.testing.assert_array_almost_equal([-10.0, 0.0], action)
action = env.step([1, 4])
np.testing.assert_array_almost_equal([10.0, 10.0], action)
action = env.step([0, 2])
np.testing.assert_array_almost_equal([-10.0, 5.0], action)
def test_check_limits(self):
obs_spec = array_spec.BoundedArraySpec((2, 3), np.int32, -10, 10)
action_spec = array_spec.BoundedArraySpec((2, 2), np.float32, -10, 10)
limits = np.array([[1, 5], [2, 2]])
with self.assertRaisesRegexp(ValueError, '.*size 2.'):
env = random_py_environment.RandomPyEnvironment(
obs_spec, action_spec=action_spec)
env = wrappers.ActionDiscretizeWrapper(env, limits)
def test_check_action_shape(self):
obs_spec = array_spec.BoundedArraySpec((2, 3), np.int32, -10, 10)
action_spec = array_spec.BoundedArraySpec((2, 2), np.float32, -10, 10)
limits = np.array([[2, 5], [2, 2]])
with self.assertRaisesRegexp(ValueError, '.*incorrect shape.*'):
env = random_py_environment.RandomPyEnvironment(
obs_spec, action_spec=action_spec)
env = wrappers.ActionDiscretizeWrapper(env, limits)
env.reset()
env.step([0, 0])
def test_discrete_spec_nd(self):
obs_spec = array_spec.BoundedArraySpec((2, 3), np.int32, -10, 10)
action_spec = array_spec.BoundedArraySpec((2, 2), np.float32, -10, 10)
limits = np.array([[2, 4], [3, 2]])
env = random_py_environment.RandomPyEnvironment(
obs_spec, action_spec=action_spec)
env = wrappers.ActionDiscretizeWrapper(env, limits)
expected_spec = array_spec.BoundedArraySpec((2, 2), np.int32, 0, limits - 1)
self.assertEqual(expected_spec, env.action_spec())
def test_discrete_spec_scalar_limit(self):
obs_spec = array_spec.BoundedArraySpec((2, 3), np.int32, -10, 10)
action_spec = array_spec.BoundedArraySpec((), np.float32, -10, 10)
limits = 3
env = random_py_environment.RandomPyEnvironment(
obs_spec, action_spec=action_spec)
env = wrappers.ActionDiscretizeWrapper(env, limits)
expected_spec = array_spec.BoundedArraySpec((), np.int32, 0,
np.asarray(limits) - 1)
self.assertEqual(expected_spec, env.action_spec())
def test_shapes_broadcast(self):
obs_spec = array_spec.BoundedArraySpec((2, 3), np.int32, -10, 10)
action_spec = array_spec.BoundedArraySpec((2, 2), np.float32, -10, 10)
limits = np.array([[2, 5]])
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.ActionDiscretizeWrapper(env, limits)
action = env.step([[0, 2], [1, 4]])
np.testing.assert_array_almost_equal([[-10.0, 0.0], [10.0, 10.0]], action)
def test_action_mapping_1d(self):
obs_spec = array_spec.BoundedArraySpec((2, 3), np.int32, -10, 10)
action_spec = array_spec.BoundedArraySpec((), np.float32, -10, 10)
limits = np.array(5)
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.ActionDiscretizeWrapper(env, limits)
action = env.step(2)
np.testing.assert_array_almost_equal(0.0, action)
action = env.step(4)
np.testing.assert_array_almost_equal(10.0, action)
