def _setup_basic_gtt_task(self, num_targets=1, reward_scale=1.0):
walker = walkers.Ant()
text_maze = arenas.padded_room.PaddedRoom(
room_size=8, num_objects=2, pad_with_walls=True)
maze_arena = arenas.MazeWithTargets(maze=text_maze)
targets = []
for _ in range(num_targets):
targets.append(
props.PositionDetector(
pos=[0, 0, 0.5],
size=[0.5, 0.5, 0.5],
inverted=False,
visible=True))
test_predicates = [predicates.MoveWalkerToRandomTarget(walker, targets)]
self._task = predicate_task.PredicateTask(
walker=walker,
maze_arena=maze_arena,
predicates=test_predicates,
targets=targets,
randomize_num_predicates=False,
reward_scale=reward_scale,
terminating_reward_bonus=2.0,
)
random_state = np.random.RandomState(12345)
self._env = composer.Environment(self._task, random_state=random_state)
self._walker = walker
self._targets = targets
def test_error_too_few_targets(self):
walker = walkers.Ant()
num_targets = 5
text_maze = arenas.padded_room.PaddedRoom(
room_size=8, num_objects=2, pad_with_walls=True)
maze_arena = arenas.MazeWithTargets(maze=text_maze)
targets = []
for _ in range(num_targets):
targets.append(
props.PositionDetector(
pos=[0, 0, 0.5],
size=[0.5, 0.5, 0.5],
inverted=False,
visible=True))
test_predicates = [predicates.MoveWalkerToRandomTarget(walker, targets)]
task = predicate_task.PredicateTask(
walker=walker,
maze_arena=maze_arena,
predicates=test_predicates,
targets=targets,
randomize_num_predicates=False,
reward_scale=1.0,
terminating_reward_bonus=2.0,
)
random_state = np.random.RandomState(12345)
env = composer.Environment(task, random_state=random_state)
with self.assertRaisesWithLiteralMatch(
RuntimeError, "The generated maze does not contain enough target "
"positions for the requested number of props (0) and targets (5): "
"got 2."
):
env.reset()
def test_too_few_predicates_raises_exception(self):
walker = walkers.Ant()
num_targets = 1
text_maze = arenas.padded_room.PaddedRoom(
room_size=8, num_objects=2, pad_with_walls=True)
maze_arena = arenas.MazeWithTargets(maze=text_maze)
targets = []
for _ in range(num_targets):
targets.append(
props.PositionDetector(
pos=[0, 0, 0.5],
size=[0.5, 0.5, 0.5],
inverted=False,
visible=True))
test_predicates = []
with self.assertRaisesWithLiteralMatch(
ValueError, "Not enough predicates for task."
" The maximum number of "
"predicates can be "
"1 but only 0 predicates provided."):
predicate_task.PredicateTask(
walker=walker,
maze_arena=maze_arena,
predicates=test_predicates,
targets=targets,
randomize_num_predicates=False,
reward_scale=1.0,
terminating_reward_bonus=2.0,
)
def _make_predicate_task(n_boxes, n_targets,
include_gtt_predicates, include_move_box_predicates,
max_num_predicates, control_timestep, time_limit):
"""Auxiliary function to construct different predicates tasks."""
walker = walkers.Ant()
skybox = dmlab_assets.SkyBox(style='sky_03')
wall = dmlab_assets.WallTextures(style='style_03')
floor = dmlab_assets.FloorTextures(style='style_03')
# Make room size become bigger once the number of objects become larger.
num_objects = n_boxes + n_targets
room_size = max(MIN_ROOM_SIZE, num_objects)
text_maze = locomotion_arenas.padded_room.PaddedRoom(
room_size=room_size, num_objects=num_objects, pad_with_walls=True)
arena = locomotion_arenas.MazeWithTargets(
maze=text_maze,
skybox_texture=skybox,
wall_textures=wall,
floor_textures=floor)
boxes = []
for _ in range(n_boxes):
boxes.append(
manipulation_props.BoxWithSites(mass=1.5, half_lengths=[0.5, 0.5, 0.5]))
targets = []
for _ in range(n_targets):
targets.append(
props.PositionDetector(
pos=[0, 0, 0.5], size=[0.5, 0.5, 0.5], inverted=False,
visible=True))
predicates = []
if include_gtt_predicates:
predicates.append(
predicates_module.MoveWalkerToRandomTarget(
walker=walker, targets=targets))
if include_move_box_predicates:
for box_idx in range(len(boxes)):
predicates.append(
predicates_module.MoveBoxToRandomTarget(
walker=walker,
box=boxes[box_idx],
box_index=box_idx,
targets=targets))
task = PredicateTask(
walker=walker,
maze_arena=arena,
predicates=predicates,
props=boxes,
targets=targets,
max_num_predicates=max_num_predicates,
randomize_num_predicates=False,
reward_scale=10.,
regenerate_predicates=False,
physics_timestep=0.005,
control_timestep=control_timestep)
env = composer.Environment(task=task, time_limit=time_limit)
return env
def test_error_if_no_predicates_found(self):
walker = walkers.Ant()
num_targets = 2
text_maze = arenas.padded_room.PaddedRoom(
room_size=8, num_objects=6, pad_with_walls=True)
maze_arena = arenas.MazeWithTargets(maze=text_maze)
targets = []
for _ in range(num_targets):
targets.append(
props.PositionDetector(
pos=[0, 0, 0.5],
size=[0.5, 0.5, 0.5],
inverted=False,
visible=True))
# Moving the walker to two targets is not possible since the walker is a
# shared object in use.
test_predicates = [predicates.MoveWalkerToTarget(walker, targets[0]),
predicates.MoveWalkerToTarget(walker, targets[1])]
task = predicate_task.PredicateTask(
walker=walker,
maze_arena=maze_arena,
predicates=test_predicates,
targets=targets[1:],
randomize_num_predicates=False,
max_num_predicates=2,
reward_scale=1.0,
terminating_reward_bonus=2.0,
)
random_state = np.random.RandomState(12345)
env = composer.Environment(task, random_state=random_state)
with self.assertRaisesWithLiteralMatch(
ValueError, "Could not find set of active predicates"
" with unique objects are after 1000 iterations."):
env.reset()
# However moving to one of the two targets is fine.
walker = walkers.Ant()
num_targets = 2
text_maze = arenas.padded_room.PaddedRoom(
room_size=8, num_objects=6, pad_with_walls=True)
maze_arena = arenas.MazeWithTargets(maze=text_maze)
targets = []
for _ in range(num_targets):
targets.append(
props.PositionDetector(
pos=[0, 0, 0.5],
size=[0.5, 0.5, 0.5],
inverted=False,
visible=True))
test_predicates = [predicates.MoveWalkerToTarget(walker, targets[0]),
predicates.MoveWalkerToTarget(walker, targets[1])]
task = predicate_task.PredicateTask(
walker=walker,
maze_arena=maze_arena,
predicates=test_predicates,
targets=targets[1:],
randomize_num_predicates=False,
max_num_predicates=1,
reward_scale=1.0,
terminating_reward_bonus=2.0,
)
random_state = np.random.RandomState(12345)
env = composer.Environment(task, random_state=random_state)
env.reset()